Publications

 

Jun Tani’s lab Publication Lists (Updated August 21, 2020) Citation Index

Book

Selected list of publications

  1. Han, D., Doya, K., & Tani, J. (2024). Synergizing habits and goals with variational Bayes. Nature Communication, (2024)15:4461. LINK
    • Behaving efficiently and flexibly is crucial for biological and artificial embodied agents. Behavior is generally classified into two types: habitual (fast but inflexible), and goal-directed (flexible but slow). While these two types of behaviors are typically considered to be managed by two distinct systems in the brain, recent studies have revealed a more sophisticated interplay between them. We introduce a theoretical framework using variational Bayesian theory, incorporating a Bayesian intention variable. Habitual behavior depends on the prior distribution of intention, computed from sensory context without goal-specification. In contrast, goal-directed behavior relies on the goal-conditioned posterior distribution of intention, inferred through variational free energy minimization. Assuming that an agent behaves using a synergized intention, our simulations in vision-based sensorimotor tasks explain the key properties of their interaction as observed in experiments. Our work suggests a fresh perspective on the neural mechanisms of habits and goals, shedding light on future research in decision making.
  2. Matsumoto, T., Ohata, W., & Tani, J. (2023). Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot using Active Inference. Entropy, 25(11), 1506. LINK
    • This study investigated how a physical robot can adapt goal-directed actions in dynamically changing environments, in real-time, using an active inference-based approach with incremental learning from human tutoring examples. Using our active inference-based model, while good generalization can be achieved with appropriate parameters, when faced with sudden, large changes in the environment, a human may have to intervene to correct actions of the robot in order to reach the goal, as a caregiver might guide the hands of a child performing an unfamiliar task. In order for the robot to learn from the human tutor, we propose a new scheme to accomplish incremental learning from these proprioceptive–exteroceptive experiences combined with mental rehearsal of past experiences. Our experimental results demonstrate that using only a few tutoring examples, the robot using our model was able to significantly improve its performance on new tasks without catastrophic forgetting of previously learned tasks.
  3. Wirkuttis, N., & Tani, J. (2021). Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework. IEEE Robotics and Automation Letters, 6(3) 6024-6031.
    PDF
    • This study investigated how social interaction among robotic agents changes dynamically depending on individual sense of agency. The study examined how regulating the complexity term to minimize free energy during training determines the dynamic characteristics of networks and affects dyadic imitative interactions. Our experiment results show that through softer regulation of the complexity term, a robot with stronger agency develops and dominates its counterpart developed with weaker agency through tighter regulation.
  4. Queißer, J. F., Jung, M., Matsumoto, T., & Tani, J. (2021). Emergence of Content-Agnostic Information Processing by a Robot Using Active Inference, Visual Attention, Working Memory, and Planning. Neural Computation, 33(9), 2353–2407.
    PDF
    • This study shows how adequate goal-directed action plans of robots can be generated by developing synergy among visual attention, visual working memory, and executive control using active inference framework. In Particular, the study demonstrates that generalization capability in mentally manipulating unlearned objects can be significantly improved when two different visual working memories are used instead of a single visual working memory. The paper explains that such generalization can be achieved by developing the so-called "content-agnostic" information processing by allowing dynamic interaction between two visual working memories.
  5. Ahmadi, A., & Tani, J. (2019). A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition. Neural Computation, 31, 2025–2074.
    PDF
    • This study introduces PV-RNN, a novel variational RNN inspired by the predictive-coding ideas. The model learns to extract the probabilistic structures hidden in fluctuating temporal patterns by dynamically changing the stochasticity of its latent states. All three processes of learning, inference, and prediction are performed by maximizing the lower bound (equal to negative free energy) which is computed as the sum of the reconstruction error and the complexity term weighted by a regularization parameter, so-called meta-prior. A set of simulation studies on learning to predict complex fluctuated temporal patterns showed that the best generalization in learning can be achieved by setting meta-prior with an adequate intermediate value, whereas setting with larger or smaller values tends to develop deterministic chaos without generalization or more random process, respectively.
  6. Murata, S., Yamashita, Y., Arie, H., Ogata, T., Sugano, S., & Tani, J. (2015). Learning to perceive the world as probabilistic or deterministic via interaction with others: a neuro-robotics experiment. IEEE Transactions on Neural Networks and Learning Systems, (4), 830-848. DOI: 10.1109/TNNLS.2015.2492140
    PDF
    • This paper introduces a variational hierarchically-organized RNN model which inherits the dynamic property of the multiple timescale RNN (MTRNN). This model was applied to predictive coding and active inference of a humanoid robot which imitatively interacts with a human-operated robot. The experiment results showed that sensory driven behavior—based on probabilistic prediction—emerges when learning proceeds with the initial context state, as a random latent variable, to follow unit Gaussian. In contrast, intentional proactive behavior with deterministic prediction emerges when adaptation of the initial context state to a precise value is allowed during the learning.
  7. Yamashita, Y., & Tani, J. (2008). Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Computational Biology, Vol.4, Issue.11, e1000220
    PDF
    • This paper examines how functional hierarchy can self-organize through sensory-motor interactions, without assuming predefined level-structured functions. A humanoid robot was implemented with so-called the multipe timescales recurrent neural network (MTRNN). The MTRNN consists of the fast neurons part and the slow neurons one which are interconnected each other within a single network. The results of the robot learning experiments showed that functional hierarchy emerges with accompanying a compositional structure such that the continuous sensory-motor flow is segmented into reusable behavior primitives in the fast neurons part and those primitives are integrated into specified goal-directed actions in the slow neuron part.
  8. Tani, J., Ito, M., & Sugita, Y. (2004). Self-organization of distributedly represented multiple behavior schemata in a mirror system: Reviews of robot experiments using RNNPB. Neural Networks, 17, 1273-1289.
    PDF
    • This paper describes a possible mechanism of mirror neurons by using frameworks analogous to predictive coding and active inference. Forward predictive models (generative models) are learned for multiple goal-directed actions distributedly in a single RNN. In action generation, units called parametric bias (PB) play role of bifurcation parameter for the RNN dynamics to generate multiple goal-directed actions. On the other hand in recognizing actions, the best PB values to fit with perceived sensory sequences are inferred by minimizing the reconstruction error. A set of robotics experiments evaluate how generalization by learning can be achieved with this distributed representation scheme.
  9. Tani, J., & Nolfi, S. (1998). Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Proc. 5th Int. Conf. on Simulation of Adaptive Behavior, (Eds) R. Pfeifer, B. Blumberg, J.A. Meyer and S.W. Wilson, MA: The MIT Press, pp.270-279. The revised version is in Neural Networks, 12, 1131-1141, 1999. 
    PDF
    • This paper introduces a predictive-coding-type RNN model of showing how continuous sensory-motor flow can be perceived as segmented into hierarchically organized primitives through anticipatory learning of local mixture of RNN experts with multiple levels. The study addresses the issue of how compositional representation can emerge solely through row sensory-motor experiences using a localist neural network model.
  10. Tani, J. (1998). An interpretation of the ‘Self’ from the dynamical systems perspective: a constructivist approach. Journal of Consciousness Studies, 5(5/6), 516-542.
    PDF
    • This study attempts to describe the notion of the "self" from dynamical systems perspective based on our robot experiments using a multimodal predictive RNN model. By investigating possible analogies between the experimental result and the phenomenological literature on the "self", we draw the conclusions that (1) the structure of the "self" corresponds to the "open dynamic structure" which is characterized by co-existence of stability in terms of goal-directedness and instability caused by embodiment; (2) the open dynamic structure causes the system's spontaneous transition to the unsteady phase where the "self" becomes aware.
  11. Tani, J. (1996). Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Trans. on Syst. Man and Cybern. Part B-Cybernetics, 26(3), 421-436. 
    PDF
    • This paper describes a neurorobotics experiment to show how 'symbolic structure' emerges as embedded in neuronal dynamics as the results of internalizing experiences of combinatorial sensory-motor interactions of robots. The action-sensation causality is learned as a forward model by using a Jordan-type recurrent neural net (RNN) which is implemented in a mobile robot. After the learning, the RNN generated on-line prediction of next sensation for given action as well as mental simulations for combinatorial action sequences without actual movements. Our dynamical system analysis showed that a finite state machine like symbolic structure emerges in a fractal-like global attractor of the RNN dynamics which is naturally situated with sensory-motor interactions with environment.
  12. Tani, J., & Fukumura, N. (1995). Embedding a grammatical description in deterministic chaos: an experiment in recurrent neural learning. Biological Cybernetics, 72, 365-370. 
    PDF
    • This paper describes how symbolic dynamics can be learned in RNN. A Jordan type RNN was trained with stochastic symbolic sequences with a grammar. The learning result showed that the stochastic symbolic sequences are reconstructed by self-organizing deterministic chaos in RNN.

 

2024

Journal papers

J110. Sawada, H., Ohata, W., & Tani, J. (2024). Human-Robot Kinaesthetic Interactions Based on the Free-Energy Principle. Accepted in IEEE-SMC, System. 1-14. LINK

J109. Han, D., Doya, K., & Tani, J. (2024). Synergizing habits and goals with variational Bayes. Nature Communication, 15:4461. LINK

J108. Tinker, T., Doya, K., & Tani, J. (2024). Intrinsic Rewards for Exploration Without Harm From Observational Noise: A Simulation Study Based on the Free Energy Principle. Neural Computation, 36 (9): 1854–1885. LINK

Others

O018. Vijayaraghavan, P.,  Queisser, J F., Flores, S V., & Tani, J. (2024). Development of Compositionality and Generalization through Interactive Learning of Language and Action of Robots. arXiv preprint arXiv:2403.19995 LINK

2023

Journal papers

J107. Matsumoto, T., Ohata, W., & Tani, J. (2023). Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot using Active Inference. Entropy, 25(11), 1506. LINK

J106. Tani, J. (2023). 自由エネルギー原理に基づく認知脳型ロボット研究 Studies of Cognitive Neurorobotics Based on the Free Energy Principle. 日本ロボット学会誌, 41(7), 609-615.

PDF

J105. Sangati, F., & Fukushima, R. (2023). PCE simulation toolkit: a platform for perceptual crossing experiment research. Frontiers in Neurorobotics. DOI 10.3389/fnbot.2023.1048817 LINK

J104. Soda, T., Ahmadreza, A., Tani, J., Honda, M., Hanakawa, T., & Yamashita, Y. (2023). Simulating Developmental Diversity: Impact of Neural Stochasticity on Atypical Flexibility and Hierarchy. Frontiers in Psychiatry, section Psychopathology. Volume 14 - 2023.

PDF

J103. Wirkuttis, N., Ohata, W., & Tani, J. (2023). Turn-Taking Mechanisms in Imitative Interaction: Robotic Social Interaction Based on the Free Energy Principle. Entropy, 25(2), 263. LINK

Conference paper with peer-reviewed

C116. Sangati, E., Sangati, F., Slors, M., & Doya, K. (2024). The Collaborative Abilities of ChatGPT Agents in a Number Guessing Game. 29th International Symposium on Artificial Life and Robotics, Beppu, Japan, January 24, 2024.

C115. Sangati, E., Sangati, F., Cheng, Y. S., & Yu-Chan Chang, A. (2023). Between Individual Brains and Collective Behavior: Multi-level Emergence in a Group Formation Task. In Artificial Life Conference Proceedings 35 (Vol. 2023, No. 1, p. 30). Sapporo, Japan, July 27, 2023.

Others

O017. Han, D., Doya, K., Li, D., & Tani, J. (2023). Habits and goals in synergy: a variational Bayesian framework for behavior. DOI: 10.31234/osf.io/v63yj LINK

O016. Sawada, H., Ohata, W., & Tani, J. (2023). Human-Robot Kinaesthetic Interaction Based on Free Energy Principle. arXiv preprint arXiv:2303.15213. LINK

2022

Journal papers

J102. Nikulin, V., & Tani, J. (2022). Initialization of Latent Space Coordinates via Random Linear Projections for Learning Robotic Sensory-Motor Sequences. Frontiers in Neurorobotics, 16:891031. DOI: 10.3389/fnbot.2022.891031 LINK

J101. Idei, H., Ohata, W., Yamashita, Y., Ogata, T., & Tani, J. (2022). Emergence of sensory attenuation based upon the free-energy principle. Scientific Report, 12:14542, DOI: 10.1038/s41598-022-18207-7

PDF

J100. Matsumoto, T., Ohata, W., Benureau, F. C., & Tani, J. (2022). Goal-directed Planning and Goal Understanding by Extended Active Inference: Evaluation Through Simulated and Physical Robot Experiments. Entropy, 24(4), 469. LINK

Conference paper with peer-reviewed

C114. Benureau, F. C., & Tani, J. (2022). Morphological Wobbling Can Help Robots Learn. 2022 IEEE International Conference on Development and Learning (ICDL). 257-264.

PDF

C113. Han, D., Kozuno, T., Luo, X., Chen, Z. Y., Doya, K., Yang, Y., & Li, D. (2022). Variational oracle guiding for reinforcement learning. In International Conference on Learning Representations. PDF

2021

Journal papers

J099. Benureau, F. C., & Tani, J. (2022). Morphological Development at the Evolutionary Timescale: Robotic Developmental Evolution. Artificial Life, 28 (1): 3–21. LINK

J098. 谷淳 (2021). 池上「生命理論としての認知科学:減算と縮約の哲学をめぐって」へのコメント. 認知科学. 28(2) 222-230. LINK

J097. Wirkuttis, N., & Tani, J. (2021). Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework. IEEE Robotics and Automation Letters, 6(3) 6024-6031.

PDF

J096. Queißer, J. F., Jung, M., Matsumoto, T., & Tani, J. (2021). Emergence of Content-Agnostic Information Processing by a Robot Using Active Inference, Visual Attention, Working Memory, and Planning. Neural Computation, 33(9), 2353–2407.

PDF

Others

O015. Lanillos, P., Meo, C., Pezzato, C., Meera, A. A., Baioumy, M., Ohata, W., Tschantz, A., Millidge, B., Wisse, M., Buckley, C. L., & Tani, J. (2021). Active Inference in Robotics and Artificial Agents: Survey and Challenges. arXiv preprint arXiv:2112.01871. LINK

O014. Idei, H., Ohata, W. Yamashita, Y., Ogata, T., & Tani, J. (2021). Sensory attenuation develops as a result of sensorimotor experience. arXiv preprint arXiv:2111.02666. LINK

O013. Han, D., Doya, K., & Tani, J. (2020). Goal-Directed Planning by Reinforcement Learning and Active Inference. arXiv preprint arXiv:2106.09938v2. LINK

2020

Journal papers

J095. Chame H. F., Ahmadi A., & Tani, J. (2020). A Hybrid Human-Neurorobotics Approach to Primary Intersubjectivity via Active Inference. Frontiers in Psychology, 11, 584869. LINK

J094. Tani, J., & White, J. (2020). Cognitive neurorobotics and self in the shared world, a focused review of ongoing research. Adaptive Behavior, 1–20. PDF

J093. Ohata, W., & Tani, J. (2020). Investigation of the Sense of Agency in Social Cognition, based on frameworks of Predictive Coding and Active Inference: A simulation study on multimodal imitative interaction. Frontiers in Neurorobotics, 14, 61.

PDF

J092. Han, D., Doya, K., & Tani, J. (2020). Self-Organization of Action Hierarchy and Compositionality by Reinforcement Learning with Recurrent Neural Networks. Neural Networks, 129, 149-162. LINK

J091. Matsumoto, T., & Tani, J. (2020). Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network. Entropy, 22(5), 564. LINK

J090. Hwang, J., Kim, J., Ahmadi, A., Choi, M., & Tani, J. (2020). Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(5), 1918-1931.

PDF

J089. Cappuccio, M. L., Kirchhoff, M. D., Alnajjar, F., & Tani, J. (2020). Unfulfilled Prophecies in Sport Performance: Active Inference and the Choking Effect. Journal of Consciousness Study, 27(3-4), 152-184. LINK

Conference paper with peer-reviewed

C112. Nikulin, V., & Tani, J. (2020). Efficient decomposition of latent representation in generative models. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 611-615, Canberra, Australia, December 1-4. LINK

C111. Han, D., Doya, K., & Tani, J. (2020). Variational recurrent models for solving partially observable control tasks. In Proceedings of the International Conference on Learning Representations (ICLR), 2020, Addis Ababa, Ethiopia, April 26-30.arXiv preprint arXiv:1912.10703v2.

PDF

C110. Chame, H. F., & Tani, J. (2020). Cognitive and motor compliance in intentional human-robot interaction. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 11291-11297. PDF

Others

O012. Chame, H. F., Ahmadi A., & Tani, J. (2020). Towards hybrid primary intersubjectivity: a neural robotics library for human science. arXiv preprint arXiv:2006.15948v1.

PDF

O011. Ohata, W., & Tani, J. (2020). Investigation of Multimodal and Agential Interactions in Human-Robot Imitation, based on frameworks of Predictive Coding and Active Inference. arXiv preprint arXiv:2002.01632. PDF.

2019

Journal papers

J088. Ahmadi, A., & Tani, J. (2019). A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition. Neural Computation, 31, 2025–2074.

PDF

J087. Zhong, J., Peniak, M., Tani, J., Ogata, T., & Cangelosi, A. (2019). Sensorimotor input as a language generalisation tool: A neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs. Autonomous Robots, 43(5), 1271-1290.

Conference paper with peer-reviewed

C109. Jung, M., Matsumoto, T., & Tani, J. (2019). Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1040-1047, Macau, China, November 4-8.

PDF

C108. Hwang, J., Wirkuttis, N., & Tani, J. (2019). A Neurorobotics Approach to Investigating the Emergence of Communication in Robots. 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 622-623.

PDF

C107. Tani, J. (2019). Accounting for the Minimal Self and the Narrative Self: Robotics Experiments Using Predictive Coding. In CEUR workshop proceedings (Vol. 2287), TOCAIS19 AAAI Spring Symposium “Towards conscious AI systems”, Stanford, USA, March 26.

2018

Journal papers

J086. Parisi, I. G., Tani, J., Weber, C., and Wermter, S. (2018). Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization. Frontiers in Neurorobotics, 12:78. link

J085. Idei, H., Murata, S., Chen, Y., Yamashita, Y., Tani, J., & Ogata, T. (2018). A Neurorobotics Simulation of Autistic Behavior Induced by Unusual Sensory Precision. Computational Psychiatry, 2, 164-182.

PDF

J084. Jung, M., Lee, H., & Tani J. (2018). Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition. Neural Networks, 105, 356-370.

PDF

J083. Choi, M., & Tani, J. (2018). Predictive Coding for Dynamic Visual Processing: Development of Functional Hierarchy in a Multiple Spatio-Temporal Scales RNN Model. Neural Computation,  30, 237–270.

PDF

Conference paper with peer-reviewed

C106. Huang, J., & Tani, J. (2018). Visuomotor Associative Learning under the Predictive Coding Framework: a Neuro-robotics Experiment. In The Proceedings of the 28th Annual Conference of the Japanese Neural Network Society (JNNS2018), pp. 30-31, Okinawa, Japan, October 26.

C105. Jung, M, & Tani, J. (2018). Adaptive Detrending for Accelerating the Training of Convolutional Recurrent Neural Networks. In The Proceedings of the 28th Annual Conference of the Japanese Neural Network Society (JNNS2018), pp. 48-49, Okinawa, Japan, October 25.

C104. Matsumoto, T., Choi, M., Jung, M., & Tani, J. (2018). Generating Goal-directed Visuomotor Plans with Supervised Learning using a Predictive Coding Deep Visuomotor Recurrent Neural Network. In The Proceedings of the 28th Annual Conference of the Japanese Neural Network Society (JNNS2018), pp. 134-135, Okinawa, Japan, October 26.

C103. Burns, F. T., Benureau, F. C. Y., & Tani, J. (2018). A Bergson-Inspired Adaptive Time Constant for the Multiple Timescales Recurrent Neural Network Model. In The Proceedings of the 28th Annual Conference of the Japanese Neural Network Society (JNNS2018), Okinawa, Japan, October 26.

C102. Benureau, F. C. Y., & Tani, J. (2018). Learning Timescales in MTRNNs. In The Proceedings of the 28th Annual Conference of the Japanese Neural Network Society (JNNS2018), pp. 177-178, Okinawa, Japan, October 26.

C101. Wirkuttis, N., Hwang, J., & Tani, J. (2018). Spontaneous Shifts of Social Alignment in Synthetic Robot-Robot Interactions. BODIS 2018: Body, Interaction, Self International Conference on Intelligent Robots and Systems 2018, Madrid, Spain, October 1.

C100. Huang, J., & Tani, J. (2018). A Dynamic Neural Network Approach to Generating Robot’s Novel Actions: A Simulation Experiment. 2018 15th International Conference on Ubiquitous Robots (UR), pp. 355-361, Hawaii, USA, June 28.

Others

O010. 谷淳 (2018). 脳型ロボット研究に基づく意識及び自由意志の統合的な理解、ベルクソン『物質と記憶』を再起動する 拡張ベルクソン主義の諸展望、書肆心水 

PDF

O009. Choi, M., Matsumoto, T., Jung, M., and Tani, J. (2018). Generating goal-directed visuomotor plans based on learning using a predictive coding type deep visuomotor recurrent neural network model. arXiv preprint arXiv:1803.02578.

PDF

2017

Journal papers

J082. White, J., & Tani, J. (2017). From Biological to Synthetic Neurorobotics Approaches to Understanding the Structure Essential to Consciousness (Part 3). American Philosophy Association Newsletter, Philosophy and Computers, 17(1), 11-22.

PDF

J081. Lee, H., Jung, M., & Tani, J. (2017). Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks. IEEE Transactions on Cognitive and Developmental Systems, (99), 1-1.

PDF

J080. Parisi, G. I., Tani, J., Weber, C., & Wermter, S. (2017). Lifelong learning of human actions with deep neural network self-organization. Neural Networks, 96 (2017), 137–149.

PDF

J079. Tatsch, C., Ahmadi, A., Bottega. F., Tani, J., & da Silva Guerra, R. (2017). Dimitri: An Open-Source Humanoid Robot with Compliant Joints. Journal of Intelligent & Robotic Systems, (91), 291–300.

J078. Hwang, J., & Tani, J. (2017). Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach. IEEE Transactions on Cognitive and Developmental Systems, 10(2), 345-358. DOI: 10.1109/TCDS.2017.2714170

J077. Tani, J., & White, J. (2017). From Biological to Synthetic Neurorobotics Approaches to Understanding the Structure Essential to Consciousness (Part 2). American Philosophy Association Newsletter, Philosophy and Computers, 16(2), 29-41.

PDF

J076. Ahmadi, A., & Tani, J. (2017). How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction. Neural Networks, 92, 3-16. DOI:10.1016/j.neunet.2017.02.015

PDF

J075. Parisi, G. I., Tani, J., Weber, C., & Wermter, S. (2017). Emergence of multimodal action representations from neural network self-organization. Cognitive Systems Research, 43, 208-221.

Conference paper with peer-reviewed

C99. Tani, J. (2017). Exploring Robotic Minds by Predictive Coding Principle. The Newsletter of the Technical Committee on Cognitive and Developmental Systems, 14(1), 4-5. Spring.

PDF

C98. Hwang, J., Kim, J., Ahmadi, A., Choi, M., & Tani, J. (2017). Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning. The 7th Joint IEEE International Conference of Developmental Learning and Epigenetic Robotics (ICDL-EpiRob 2017), pp. 132-139, Lisbon, Portugal, September. PDF

Others

O008. Ahmadi, A., & Tani, J. (2017). Bridging the Gap between Probabilistic and Deterministic Models: A Simulation Study on a Variational Bayes Predictive Coding Recurrent Neural Network Model. International Conference on Neural Information Processing, pp. 760-769, Guangzhou, China, November. PDF

2016

Journal papers

J074. Lyon, C. et al. (2016). Embodied language learning and cognitive bootstrapping: Methods and design principles. International Journal of Advanced Robotics Systems, 13:105. DOI:10.5772/63462

J073. White, J., & Tani, J. (2016). From biological to synthetic neurorobotics approaches to understanding the structure essential to consciousness. (Part 1). American Philosopher Association Newsletter, Philosophy and Computers, 16(1), 13-23.

PDF

Conference paper with peer-reviewed

C097. Ahamdi, A., & Tani, J. (2016). Towards Robustness to Fluctuated Perceptual Patterns by a Deterministic Predictive Coding Model in a Task of Imitative Synchronization with Human Movement Patterns. Proc. of International Conference on Neural Information Processing, pp. 393-402, October. PDF (got Excellent Paper Award)

C096. Hwang, J., Jung, M., & Tani, J. (2016). A Deep Learning Approach for Seamless Integration of Cognitive Skills for Humanoid Robots. In 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pp. 59-65.

PDF

C095. Chen, Y., Murata, S., Arie, H., Ogata, T., Tani, J., & Sugano, S. (2016). Emergence of Interactive Behaviors between Two Robots by Prediction Error Minimization Mechanism. In 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pp. 302-307.

PDF

Others

O007. Choi, M., & Tani, J. (2016). Predictive Coding for Dynamic Vision : Development of Functional Hierarchy in a Multiple Spatio-Temporal Scales RNN Model. arXiv:1606.01672v2. PDF

O006. Lee, H., Jung, M., & Tani, J., (2016). Characteristics of Visual Categorization of Long-Concatenated and Object-Directed Human Actions by a Multiple Spatio-Temporal Scales Recurrent Neural Network Model. arXiv:1602.01921v1.

PDF

2015

Journal papers

J072. Murata, S., Yamashita, Y., Arie, H., Ogata, T., Sugano, S., & Tani, J. (2015). Learning to perceive the world as probabilistic or deterministic via interaction with others: a neuro-robotics experiment. IEEE Transactions on Neural Networks and Learning Systems, (4), 830-848. DOI: 10.1109/TNNLS.2015.2492140

PDF

J071. Park, G., & Tani, J. (2015). Development of compositional and contextual communicable congruence in robots by using dynamic neural network models. Neural Networks, 72, 109-122.

PDF

J070. Jung, M., Hwang, J., & Tani, J. (2015). Self-organization of spatio-temporal hierarchy via learning of dynamic visual image patterns on action sequences. PLoS One, 10(7): e0131214. DOI:10.1371/journal.pone.0131214 PDF

Conference paper with peer-reviewed

C094. Park, G., & Tani, J., (2015). Development of Compositional and Contextual Communication of Robots by using the Multiple Timescales Dynamic Neural Network. Proc. of the Fifth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob2015), pp. 176-181, August.

PDF

C093. Hwang, J., Jung, M., Madapana, N., Kim, J., Choi, M., & Tani, J. (2015). Achieving “Synergy” in Cognitive Behavior of Humanoids via Deep Learning of Dynamic Visuo-Motor-Attentional Coordination. Proc. of 2015 IEEE-RAS International Conference on Humanoid Robots, pp. 817-824.

PDF

Others

O005. Park, G. (2015). Development of Compositional and Contextual Communicative Skills of Robot by Using a Neuro-Dynamic Model. MS Thesis.

PDF

2014

Journal papers

J069. Murata, S., Arie, H., Ogata, T., Sugano, S., & Tani, J. (2014). Learning to generate proactive and reactive behavior using a dynamic neural network model with time-varying variance prediction mechanism. Advanced Robotics, 28(17), 1189-1203. DOI: 10.1080/01691864.2014.916628

J068. Tani, J. (2014). Self-Organization and Compositionality in Cognitive Brains: A Neuro-Robotics Study. Proceedings of the IEEE, Special Issue on Cognitive Dynamic Systems, 102(4), 586-605. 

PDF

J067. Komatsu, M., Namikawa, J., Chao, Z. C., Nagasaka, Y., Fujii, N., Nakamura, K., & Tani, J. (2014). An artificial network model for estimating the network structure underlying partially observed neuronal signals. Neuroscience Research, 81-82, 69-77. DOI: 10.1016/j.neures.2014.02.005

Conference paper with peer-reviewed

C092. Jung, M., Hwang, J., & Tani, J. (2014). Multiple Spatio-Temporal Scales Neural Network for Contextual Visual Recognition of Human Actions. Proc. of the Fourth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob2014), pp. 227-233, Genoa, Italy, October.

PDF

C091. Murata, S., Yamashita, Y., Arie, H., Ogata, T., Tani, J., & Sugano. S. (2014). Generation of Sensory Reflex Behavior versus Intentional Proactive Behavior in Robot Learning of Cooperative Interactions with Others. In Proceedings of the Fourth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2014), pp. 234-240, Genoa, Italy, October.

C090. Tan, B.H., Tang, H., Yan, R., & Tani, J. (2014). A Flexible and Robust Robotic Arm Design and Skill Learning by Using Recurrent Neural Networks. In Proc. of IEEE Int. Conf. on Intelligent Robots and Systems (IROS2014), pp. 522-529, September.

C089. Murata, S., Arie, H., Ogata, T., Tani, J., & Sugano, S. (2014). Learning and Recognition of Multiple Fluctuating Temporal Patterns Using S-CTRNN. The 24th International Conference on Artificial Neural Networks (ICANN 2014), pp. 9-16, Hamburg, Germany, September.

Others

O004. Tani, J., Maniadakis, M., & Paine, RW. (2014). Understanding Higher-Order Cognitive Brain Mechanisms by Conducting Evolutional Neuro-robotics Experiments. In The Horizons of Evolutionary Robotics, pp. 219-236, ed., P.A. Vargas, E.A. Di Paolo, I. Harvey and P. Husband, MIT Press.

2013

Journal papers

J066. Murata, S., Namikawa, J., Arie, H., Sugano, S., & Tani, J. (2013). Learning to reproduce fluctuating time series by inferring their time-dependent stochastic properties: Application in robot learning via tutoring. IEEE Transactions on Autonomous Mental Development, 5(4), 298-310. DOI: 10.1109/TAMD.2013.2258019 

PDF

J065. Jeong, S., Park, Y., Mallipeddia, P., Tani, J., & Lee, M. (2013). Goal-oriented Behavior Sequence Generation based on Semantic Commands using Multiple Timescales Recurrent Neural Network with Initial State Correction. Neurocomputing, 129, 67-77.

J064. Alnajjar, F., Yamashita, Y., & Tani, J. (2013). The Hierarchical and Functional Connectivity of Higher-order Cognitive Mechanisms: Neurorobotic Model to Investigate the Stability and Flexibility of Working Memory. Frontiers in Neurorobotics, Vol. 7, Article 2, February.

PDF

Conference paper with peer-reviewed

C088. Murata, S., Namikawa, J., Arie, H., Tani, J., & Sugano, S. (2013). Development of Proactive and Reactive Behavior via Meta-Learning of Prediction Error Variance. The 20th International Conference on Neural Information Processing, pp. 537-544, Daegu, Korea, November.

C087. Murata, S., Namikawa, J., Arie, H., Tani, J., & Sugano, H. (2013). Learning to Reproduce Fluctuating Behavioral Sequences Using a Dynamic Neural Network Model with Time-Varying Variance Estimation Mechanism. The Third Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, pp. 1-6, Osaka, Japan, August.

2012

Journal papers

J063. Yamashita, Y., & Tani, J. (2012). Spontaneous Prediction Error Generation in Schizophrenia.  PLoS One, 7(5): e37843. doi:10.1371/journal.pone.0037843

PDF

J062. Maniadakisa, M., Trahaniasa, P., & Tani, J. (2012). Self-organizing high-order cognitive functions in artificial agents: implications for possible prefrontal cortex mechanisms. Neural Networks, 33, 76-87. 

PDF

J061. Nishide, S., Tani, J., Takahashi, T., Okuno, H.G., & Ogata, T. (2012) Tool-Body assimilation of humanoid robot using neuro-dynamical system. IEEE Trans. on Autonomous Mental Development, 14, 139-149.

Conference paper with peer-reviewed

C086. Nishide, S., Tani, J., Okuno, H.G., & Ogata, T. (2012). Self-organization of Object Features Representing Motion Using Multiple Timescales Recurrent Neural Network. In The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, June.

C085. Komatsu, M., Namikawa, J., Tani, J., Chao, C.Z., Nagasaka, Y., Fujii, N., & Nakamura, K. (2012): Estimation of functional brain connectivity from electrocorticograms using an artificial network model. Proc. of Int. Joint. Conf. of Neural Networks (IJCNN2012), June.

2011

Journal papers

J060. Arie, H., Arakaki, T., Sugano, S., & Tani, J. (2011). Imitating others by composition of primitive actions: a neuro-dynamic model. Robotics and Autonomous Systems, 60, 729-741.

PDF

J059. Tobari, Y., Okumura, T., Tani, J., & Okanoya, K. (2011). A direct neuronal connection between the telencephalic nucleus robustus arcopallialis and the nucleus nervi hypoglossi, pars tracheosyringealis in Bengalese finches (Lonchura striata var. domestica). Neuroscience Research, 71(4), 361-368.

J058. Namikawa, J., Nishimoto, R., & Tani, J. (2011). A neurodynamic account of spontaneous behavior. PLoS Computational Biology, Vol. 7, Issue 10, e1002221. 

PDF

J057. Rohlfing, K.J., & Tani, J. (2011). Grounding language in action. IEEE Transactions on Autonomous Mental Development, 3(2), 109-112.

PDF

J056. Jeong, S., Arie, H., Lee, M., & Tani, J. (2011). Neuro-robotics study on integrative learning of proactive visual attention and motor behaviors. Cognitive Neurodynamics, 6, 43-59.

PDF

J055. Sugita, Y., Tani, J., & Butz, M.V. (2011). Simultaneously emerging braitenberg codes and compositionality. Adaptive Behavior, 19(5), 295-316. 

PDF

J054. Yamashita, Y., Okumura, T., Okanoya, K., & Tani, J. (2011). Cooperation of deterministic dynamics and random noise in production of complex syntactical avian song sequences: a neural network model. Frontiers in Computational Neuroscience, 5(18), 1-12.

PDF

J053. Nishide, S., Tani, J., Okuno, H.G. & Ogata, T. (2011). Towards written text recognition based on handwriting experiences using recurrent neural network. Advanced Robotics, 25(17), 2173-2187.

J052. Hinoshita, W., Arie, H., Tani, J., Okuno, H. & Ogata, T. (2011). Emergence of hierarchical structure mirroring linguistic composition in a recurrent neural network. Neural Networks, 24, 311-320.

PDF

Conference paper with peer-reviewed

C084. Alnajjar, F., Yamashita, Y., & Tani, J. (2011). Formulating a Cognitive Branching Task by MTRNN:A Robotic Neuroscience Experiments to Simulate the PFC and its Neighboring Regions. Advances in Cognitive Neurodynamics (III): Proceedings of the Third International Conference on Cognitive Neurodynamics, pp. 267-274.

C083. Yamashita, Y., & Tani, J. (2011). Neurodynamical account for altered awareness of action in schizophrenia: a synthetic neuro-roboic study. Advances in Cognitive Neurodynamics (III): Proceedings of the Third International Conference on Cognitive Neurodynamics, pp. 275-280.

C082. Namikawa, J., Nishimoto, R., Arie, H., & Tani, J. (2011). Synthetic approach to understanding meta-level cognition of predictability in generating cooperative behavior. Advances in Cognitive Neurodynamics (III): Proceedings of the Third International Conference on Cognitive Neurodynamics, pp. 615-611.

PDF

C081. Maniadakis, M., Tani, J., & Trahanias, P. (2011). Ego-centric and allo-centric abstraction in self-organized hierarchical neural networks. In 2011 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2, 1-6, Frankfurt, Germany, August.

C080. Peniak, M., Marocco, D., Tani, J., Yamashita, Y., Fischer, K., & Cangelosi, A. (2011). Multiple time scales recurrent neural network for complex action acquisition. In 2011 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Frankfurt, Germany, August.

C079. Nishide, S., Tani, T., Okuno, H.G., & Ogata, T. (2011). Handwriting prediction based character recognition using recurrent neural network. 2011 IEEE Int. Conf. on Sysntems, Man, and Cybernetics, pp. 2549-2554, Anchorage, USA, October.

C078. Jeong, S., Park, Y., Arie, H., Tani, J., & Lee, M. (2011). Goal-oriented behavior generation for visually-guided manipulation task. Lecture Notes in Computer Science, Proc. 18th Int. Conf, ICONIP 2011, 7062, 501-508, Shanghai, China, November.

C077. Awano, H., Nishide, S., Arie, H., Tani, J., Takahashi, T., Okuno, H.G., & Ogata, T. (2011). Use of a sparse structure to improve learning performance of recurrent neural networks. Lecture Notes in Computer Science, Proc. 18th Int. Conf, ICONIP 2011, 7064, 323-331, Shanghai, China, November.

Others

O003. Nishimoto, R., & Tani, J. (2011). Schemata Learning. In Perception-Action Cycle. Springer New York, 219-241.

2010

Journal papers

J051. Cangelosi, A., Metta, G., Sagerer, G., Nolfi, S., Nehaniv, C.L., Fischer, K., Tani, J., Belpaeme, B., Sandini, G., Fadiga, L., Wrede, B., Rohlfing, K., Tuci, E., Dautenhahn, K., Saunders, J. & Zeschel, A. (2010). Integration of action and language knowledge: A roadmap for developmental robotics. IEEE Transactions on Autonomous Mental Development, 2(3), 167-195.

PDF

J050. Tani, J. (2010). Studies of symbols from ‘Robot Science’. Journal of the Robotics Society of Japan, 28(4), 522-531.

PDF

 (in Japanese)

J049. Namikawa, J. & Tani, J. (2010). Learning to imitate stochastic time series in a compositional way by chaos. Neural Networks, 23, 625-638. 

PDF

Conference paper with peer-reviewed

C076. Nishide, S., Ogata, T., Tani, J., Takahashi, T., Komatani, K., & Okuno, HG. (2010). Motion generation based on reliable predictability using self-organized object features. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2010), pp. 3453-3458, Taipei, Taiwan, October.

C075. Arie, H., Endo, T., Jeong, S., Lee, M., Sugano, S., & Tani, J. (2010). Integrative learning between language and action: a neuro-robotics experiment. Lecture Notes in Computer Science, Proc. 20th Int. Conf. on Artificial Neural Networks (ICANN2010), 6353, 256-265, Thessaloniki, Greece, September.

PDF

C074. Jeong, S., Lee, M., Arie, H., & Tani, J. (2010). Developmental learning of integrating visual attention shifts and bimanual object grasping and manipulation tasks. Proc. IEEE 9th Int. Conf. on Development and Learning (ICDL2010), pp. 165-170, Ann Arbor, USA, August. 

PDF

C073. Maniadakis, M., Trahanias, P., & Tani, J. (2010). Self-organized executive control functions. Proc. 2010 Int. Joint Conf. on Neural Networks (IJCNN2010), pp. 3633-3640, Barcelona, Spain, July. 

PDF

C072. Hinoshita, W., Arie, H., Tani, J., Ogata, T., & Okuno, H.G. (2010). Recognition and generation of sentences through self-organizing linguistic hierarchy using MTRNN. Lecture Notes in Artificial Intelligence, Proc. 23rd Int. Conf. on Industrial Engineering and Other Applications of Applied Intelligence Systems (IEA/AIE2010), 6098, 42-51, Cordoba, Spain, June.

2009

Journal papers

J048. Maniadakis, M., Trahanias, P., & Tani, J. (2009). Explorations on artificial time perception. Neural Networks, 22, 509-517.

PDF

J047. Tani, J. (2009). Autonomy of ‘Self’ at criticality: The perspective from synthetic neuro-robotics. Adaptive Behavior, 17(5), 421-443.

PDF

J046. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2009). Self-organization of dynamic object features based on bidirectional training. Advanced Robotics, 23, 2035-2057.

J045. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2009). Autonomous motion generation based on reliable predictability. Journal of Robotics and Mechatronics, 21(4), 478-488.

J044. Nishimoto, R., & Tani, J. (2009). Development of hierarchical structures for actions and motor imagery: a constructivist view from synthetic neuro-robotics study. Psychological Research, 73, 545-558. 

PDF

J043. Arie, H., Endo, T., Arakaki, T., Sugano, S., & Tani, J. (2009). Creating novel goal-directed actions at criticality: a neuro-robotic experiment. New Mathematics and Natural Computation, 5(1), 307-334.

PDF

J042. Maniadakis, M., & Tani, J. (2009). Acquiring rules for rules: neuro-dynamical systems account for meta-cognition. Adaptive Behavior, 17(1), 58-80. 

PDF

J041. Igari, I., & Tani, J. (2009). Incremental learning of sequence patterns with a modular network model. Neurocomputing, 72, 1910-1919.

PDF

Conference paper with peer-reviewed

C071. Arie, H., Endo, T., Arakaki, T., Sugano, S., & Tani, J. (2009). A neuro-dynamical model for understanding mechanisms of goal-directed action imitation. Proc. 3rd Int. Symp. on Mobiligence, pp. 46-51, Awaji, Japan, November.

C070. Namikawa, J., & Tani, J. (2009). Learning to generate probabilistic event transition sequences via chaotic dynamics. Proc. 3rd Int. Symp. on Mobiligence, pp. 129-132, Awaji, Japan, November.

C069. Nishide, S., Nakagawa, T., Ogata, T., Tani, J., Takahashi, T., & Okuno, H.G. (2009). Modeling tool-body assimilation using second-order recurrent neural network. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2009), pp. 5376-5381, St. Louis, USA, October. 

PDF

C068. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2009). Analysis of motion searching based on reliable predictability using recurrent neural network. Proc. 2009 IEEE/ASME Int. Conf. on Advanced Intelligent Mechatronics (AIM2009), pp. 192-197, Singapore, July.

C067. Namikawa, J., & Tani, J. (2009). Learning to imitate stochastic time series in a compositional way by chaos. Proc. IEICE Technical Report on Neurocomputing, 109(125), 25-30, Ikoma, Japan, July.

C066. Maniadakis, M., Tani, J., & Trahanias, P. (2009). Time perception in shaping cognitive neurodynamics of artificial agents. Proc. 2009 Int. Joint Conf. on Neural Networks (IJCNN2009), pp. 1993-2000, Atlanta, USA, June.

C065. Rybicki, L., Sugita, Y., & Tani, J. (2009). Reinforcement learning of multiple tasks using parametric bias. Proc. 2009 Int. Joint Conf. on Neural Networks (IJCNN2009), pp. 2732-2739, Atlanta, USA, June.

C064. Nishimoto, R., & Tani, J. (2009). Development process of functional hierarchy for actions and motor imagery. Proc. IEEE 8th Int. Conf. on Development and Learning (ICDL2009), pp. 1-6, Shanghai, China, June.

C063. Arie, H., Endo, T., Arakaki, T., Sugano, S., & Tani, J. (2009). Creating novel goal-directed actions using chaotic dynamics. Proc. IEEE 8th Int. Conf. on Development and Learning (ICDL2009), pp. 1-6, Shanghai, China, June.

C062. Ogata, T., Yokoya, R., Tani, J., Komatani, K., & Okuno, H.G. (2009). Prediction and imitation of other's motions by reusing own forward-inverse model in robots. Proc. 2009 IEEE Int. Conf. on Robots and Automation (ICRA2009), pp. 4144-4149, Kobe, Japan, May.

2008

Journal papers

J040. Tani, J. (2008). Objectifying the subjective self: An account from a synthetic robotics approach. Constructivist Foundations, 4(1), 28-30.

PDF

J039. Namikawa, J., & Tani, J. (2008). Building recurrent neural networks to implement multiple attractor dynamics using the gradient descent method. Advances in Artificial Neural Systems, Vol. 2009, Article ID 846040.

PDF

J038. Yamashita, Y., & Tani, J. (2008). Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Computational Biology, Vol.4, Issue.11, e1000220.

PDF

J037. Namikawa, J., & Tani, J. (2008). A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance. Neural Networks, 21, 1466-1475.

PDF

J036. Yamashita, Y., Takahashi, M., Okumura, T., Ikebuchi, M., Yamada, H., Suzuki, M., Okanoya, K., & Tani, J. (2008). Developmental learning of complex syntactical song in theBengalese finch: A neural network model. Neural Networks, 21, 1224-1231.

PDF

J035. Tani, J., Nishimoto, R., & Paine, R.W. (2008). Achieving ‘organic compositionality’ through self-organization: Reviews on brain-inspired robotics experiments. Neural Networks, 21, 584-603.

PDF

J034. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2008). Predicting object dynamics from visual images through active sensing experiences. Advanced Robotics, 22(5), 527-546. 

PDF

J033. Nishimoto, R., Namikawa, J., & Tani, J. (2008). Learning multiple goal-directed actions through self-organization of a dynamic neural network model: a humanoid robot experiment. Adaptive Behavior, 16(2/3), 166-181. 

PDF

J032. Tani, J., Nishimoto, R., Namikawa, J., & Ito, M. (2008). Codevelopmental learning between human and humanoid robot using a dynamic neural-network model. IEEE Trans. on Syst. Man and Cybern. Part B-Cybernetics, 38(1), 43-59. 

PDF

Conference paper with peer-reviewed

C061. Tani, J. (2008). Co-developmental learning between humanoids and human via force and intentionality interaction. Proc. 4th Workshop on Anticipatory Behavior in Adaptive Learning Systems (ABiALS2008), Munich, Germany.

C060. Nishide, S., Ogata, T., Yokoya, R., Tani, J., Komatani, K., & Okuno, H.G. (2008). Active sensing based dynamical object feature extraction. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2008), pp. 1-7, Nice, France, September. 

PDF

C059. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2008). Analysis of reliable predictability based motion generation using RNNPB. Proc. Int. Conf. on Soft Computing and Intelligent Systems and Int. Symposium on advanced Intelligent Systems (SCIS&ISIS2008), pp. 305-310, Nogoya, Japan, September.

PDF

C058. Sugita, Y., & Tani, J. (2008). A sub-symbolic process underlying the usage-based acquisition of a compositional representation: Results of robotic learning experiments of goal-directed actions. Proc. 7th IEEE Int. Conf. on Development and Learning (ICDL2008), pp. 127-132, Monterey, USA, August.

PDF

C057. Maniadakis, M., & Tani, J. (2008). Dynamical systems account for meta-level cognition. Lecture Notes in Artificial Intelligence, 5040, 311-320, Proc. 10th Int. Conf. on Simulation of Adaptive Behavior (SAB2008), Osaka, Japan, July.

C056. Sugita, Y., & Tani, J. (2008). Acquiring a functionally compositional system of goal-directed actions of a simulated agent. Lecture Notes in Artificial Intelligence, Proc. 10th Int. Conf. on Simulation of Adaptive Behavior (SAB2008), 5040, 331-341, Osaka, Japan, July.

PDF

C055. Nishide, S., Ogata, T., Yokoya, R., Tani, J., Komatani, K., & Okuno, H.G. (2008). Object dynamics prediction and motion generation based on reliable predictability. Proc. IEEE-RAS Int. Conf. on Robots and Automation (ICRA2008), pp. 1608-1614, Pasadena, USA, May.

PDF

2007

Journal papers

J031. Tani, J. (2007). On the interactions between top-down anticipation and bottom-up regression. Frontiers in Neurorobotics, Vol. 1, Article 2.

PDF

J030. Okumura, T., Okanoya, K., & Tani, J. (2007). Application of light-cured dental adhesive resin for mounting electrodes or microdialysis probes in chronic experiments. Journal of Visualized Experiments, 6, 249-1~249-10.

J029. Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2007). Experience-based imitation using RNNPB. Advanced Robotics, 21(12), 1351-1367.

PDF

J028. Arie, H., Ogata, T., Tani, J., & Sugano, S. (2007). Reinforcement learning of a continuous motor sequence with hidden states. Advanced Robotics, Special Issue on Robotic Platforms for Research in Neuroscience, 21(10), 1215-1229.

PDF

Conference paper with peer-reviewed

C054. Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2007). Discovery of other individuals by projecting a self-model through imitation. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2007), pp. 1009-1014, San Diego, USA, October-November.

C053. Ogata, T., Murase, M., Tani, J., Komatani, K., & Okuno, H.G. (2007). Two-way translation of compound sentences and arm motions by recurrent neural networks. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2007), pp. 1858-1863, San Diego, USA, October-November.

PDF

C052. Arie, H., Sugano, S., & Tani, J. (2007). Constructive approach to understanding the active learning process of adaptation within a given task environment. Proc. 2nd Int. Symp. on Mobiligence, pp. 77-80, Awaji, Japan, July.

C051. Yamashita, Y., Okumura, T., Okanoya, K., & Tani, J. (2007). Function of the sensori-motor nucleus NIf in generation of complex syntactical song in the Bengalese Finch. Proc. 2nd Int. Symp. on Mobiligence, pp. 101-104, Awaji, Japan, July.

C050. Nishide, S., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2007). Predicting Object Dynamics from Visual Images through Active Sensing Experiences. Proc. of IEEE Int. Conf. on Robotics and Automation (ICRA2007), pp. 2501-2506, Roma, Italy, April. 

PDF

C049. Ogata, T., Matsumoto, S., Tani, J., Komatani, K., & Okuno, H.G. (2007). Human-Robot Cooperation using Quasi-symbols Generated by RNNPB Model. Proc. of IEEE Int. Conf. on Robotics and Automation (ICRA2007), pp. 2156-2161, Roma, Italy, April.

2006

Journal papers

J027. Ito, M., Noda, K., Hoshino, Y., & Tani, J. (2006). Dynamic and interactive generation of object handling behaviors by a small humanoid robot using a dynamic neural network model. Neural Networks, 19, 323-337.

PDF

J026. Tobari, Y., Okumura, T., Tani, T., & Okanoya, K. (2006). Non-singing female Bengalese Finches (Lonchura striata var. domestica) possess neuronal projections connecting a song learning region to a song motor region. Ornithological Science, 5, 47-55.

Conference paper with peer-reviewed

C048. Arie, H., Namikawa, J., Ogata, T., Tani, J., & Sugano, S. (2006). Reinforcement learning algorithm with CTRNN in continuous action space. Lecture Notes in Computer Science, Int. Conf. on Neural Information Processing (ICONIP2006), 4232, 387-396, Hong Kong, China, October.

C047. Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2006). Experience Based Imitation Using RNNPB. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2006), pp. 3669-3674, Beijing, China, October.

C046. Noda, K., Ito, M., Hoshino, Y., & Tani, J. (2006). Dynamic generation and switching of object handling behaviors by a humanoid robot using a recurrent neural network model. Lecture Notes in Artificial Intelligence, Int. Conf. on the Simulation of Adaptive Behavior (SAB’06), 4095, 185-196, Rome, Italy, September.

C045. Igari, I., Hirata, C., & Tani, J. (2006). Computational model for sequence learning: generalization and differentiation dynamics of learning modules. Proc. 5th Int. Conf. on Development and Learning (ICDL2006), pp. 45-1~45-6, Bloomington, USA, May-June.

C044. Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H.G. (2006). Robot imitation from Active-sensing experiences. Proc. 5th Int. Conf. on Development and Learning (ICDL2006), pp. 27-1~27-6, Bloomington, USA, May-June.

2005

Journal papers

J025. Ogata, T., Ohba, H., Tani, J., Komatani, K., & Okuno, H.G. (2005). Extracting multimodal dynamics of objects using RNNPB. Journal of Robotics and Mechatronics, 17(6), 681-688.

J024. Ogata, T., Sugano, S., & Tani, J. (2005). Open-end human-robot interaction from the dynamical systems perspective: mutual adaptation and incremental learning. Advanced Robotics, 19(6), 651-670.

J023. Ogata, T., Sugano, S., & Tani, J. (2005). Acquisition of motion primitives of robot in human-navigation task. Journal of Japanese Society for Artificial Intelligence, 20(3), 188-196.

PDF

J022. Paine, R.W., & Tani, J. (2005). How hierarchical control self-organizes in artificial adaptive systems. Adaptive Behavior, 13(3), 211-225. 

PDF

J021. Sugita, Y., & Tani, J. (2005). Learning semantic combinatoriality from the interaction between linguistic and behavioral processes. Adaptive Behavior, 13(1), 33-52.

PDF

Conference paper with peer-reviewed

C043. Tani, J. (2005). Self-organization of neuronal dynamical structures through sensory-motor experiences of robots. Proc. Workshop on Intelligence Dynamics, IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids2005), pp. 32-37, Tsukuba, Japan, December.

C042. Ogata, T., Ohba, H., Tani, J., Komatani, K., & Okuno, H.G. (2005). Extracting multi-modal dynamics of objects using RNNPB. Proc. 2005 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2005), pp. 160-165, Edmonton, Canada, August.

C041. Sugita, Y., & Tani, J. (2005). Learning segmentation of behavior to acquire situated combinatorial semantics. Proc. Workshop on Neural-Symbolic Learning and Reasoning, 19th Int. Joint Conf. on Artificial Intelligence (IJCAI-05), pp. 1-6, Edinburgh, UK, August.

2004

Journal papers

J020. Ito, M., & Tani, J. (2004). On-line imitative interaction with a humanoid robot using a dynamic neural network model of a mirror system. Adaptive Behavior, 12(2), 93-115. 

PDF

J019. Tani, J. (2004). The dynamical systems accounts for phenomenology of immanent time: an interpretation by revisiting a robotics synthetic study. Journal of Consciousness Studies, 11(9), 5-24.

PDF

J018. Paine, R.W., & Tani, J. (2004). Motor primitive and sequence self-organization in a hierarchical recurrent neural network. Neural Networks, 17, 1291-1309.

PDF

J017. Tani, J., Ito, M., & Sugita, Y. (2004). Self-organization of distributedly represented multiple behavior schemata in a mirror system: Reviews of robot experiments using RNNPB. Neural Networks, 17, 1273-1289. 

PDF

J016. Nishimoto, R., & Tani, J. (2004). Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems. Neural Networks, 17, 925-933.

PDF

Conference paper with peer-reviewed

C040. Tani, J., & Ito, M. (2004). Interacting with NeuroCognitive Robots: A Dynamical System View. Proc. 2nd Int. Workshop on Man-Machine Symbiotic Systems, pp. 123-134, Kyoto, Japan, November.

PDF

C039. Ogata, T., Sugano, S., & Tani, J. (2004). Acquisition of Motion Primitives of Robot in Human-Navigation Task: Towards Human-Robot Interaction based on ‘Quasi-Symbol. Proc. 2nd Int. Workshop on Man-Machine Symbiotic Systems, pp. 315-326, Kyoto, Japan, November.

C038. Ito, M., & Tani, J. (2004). Generalization in Learning Multiple Temporal Patterns Using RNNPB. Proc. 11th Int. Conf. on Neural Information Processing (ICONIP2004), 3316, 592-598, Calcutta, India, edited by Pal N.R., Kasabov N., Mudi R.K., Pal S., Parui S.K., Springer-Verlag, November.

PDF

C037. Tani, J., Ito, M., & Sugita, Y. (2004). Review of a dynamic neural network scheme for synthesizing cognition of robots and humanoids. Proc. IEEE-RAS/RSJ Int. Conf. on Humanoid Robots (Humanoids2004), CD1-20, Los Angeles, USA, November.

C036. Ito, M., & Tani, J. (2004). Joint attention between a humanoid robot and users in imitation game. Proc. 3rd Int. Conf. on Development and Learning (ICDL'04), La Jolla, USA, October.

PDF

C035. Ogata, T., Matsunaga, M., Sugano, S., & Tani, J. (2004). Human-robot collaboration using behavioral primitives. Proc. 2004 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2004), pp. 1592-1597, Sendai, Japan, September-October.

PDF

C034. Ogata, T., Sugano, S., & Tani, J. (2004). Open-end human robot interaction from the dynamical systems perspective: Mutual adaptation and incremental learning. Lecture Notes in Artificial Intelligence, Int. Conf. on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE2004), 3029, 435-444, Ottawa, Canada, May.

C033. Sugita, Y., & Tani, J. (2004). A holistic approach to compositional semantics: a connectionist model and robot experiments. Advances in Neural Information Processing Systems 16 (NIPS2003), pp. 969-976, Vancouver and Whistler, Canada, December, edited by Thrun S., Saul L.K., Scholkopf B., The MIT Press.

PDF

C032. Sugita, Y., & Tani, J. (2004). A connectionist approach to learn association between sentences and behavioral patterns of a robot. Proc. 8th Int. Conf. on Simulation of Adaptive Behavior (SAB’04), pp. 467-476, Los Angeles, USA, July, edited by Schaal S., Ljspeert A., Billard A., Vijayakumar S., Hallam J., Meyer J., The MIT Press.

C031. Paine, R.W., & Tani, J. (2004). Adaptive motor primitive and sequence formation in a hierarchical recurrent neural network. Proc. 8th Int. Conf. on Simulation of Adaptive Behavior (SAB’04), pp. 274-283, Los Angeles, USA, July, edited by Schaal S., Ljspeert A., Billard A., Vijayakumar S., Hallam J., Meyer J., The MIT Press.

C030. Paine, R.W., & Tani, J. (2004). Evolved motor primitives and sequences in a hierarchical recurrent neural network. Proc. Genetic and Evolutionary Computation Conference (GECCO2004), pp. 603-614, Seattle, USA, June, edited by Deb K., Springer-Verlag.

C029. Ito, M., & Tani, J. (2004). On-line imitative interaction with a humanoid robot using a mirror neuron model. Proc. 2004 IEEE Int. Conf. on Robotics & Automation (ICRA2004), pp. 1071-1076, New Orleans, USA, April-May.

2003

Journal papers

J015. Tani, J., & Ito, M. (2003). Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment. IEEE Trans. on Syst. Man and Cybern. Part A- Systems and Humans, 33(4), 481-488. 

PDF

J014. Tani, J. (2003). Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Neural Networks, 16(1), 11-23. 

ps.Z
PDF

Conference paper with peer-reviewed

C028. Ogata, T., Masago, N., Sugano, S., & Tani, J. (2003). Interactive learning in human-robot collaboration. Proc. 2003 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2003), pp. 162-167, Las Vegas, USA, October.

C027. Ogata, T., Masago, N., Sugano, S., & Tani, J. (2003). Collaboration development through interactive learning between human and robot. Proc. 3rd Int. Workshop on Epigenetic Robotics, pp. 99-106, Boston, USA, August, edited by Prince C.G. and others.

C026. Nishimoto, R., & Tani, J. (2003). Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems. Lecture Notes in Computer Science, Int. Work-Conf. on Artificial and Natural Neural Networks (IWANN2003), 2686, 422-429, Mao, Menorca, Spain, June.

Others

O002. Tani, J. (2003). Symbols and dynamics in embodied cognition: revisiting a robot experiment. Anticipatory Behavior in Adaptive Learning Systems, edited by Butz M.V., Sigaud O., Gerard P., Springer-Verlag, 167-178.

PDF

2002

Journal paper

J013. Tani, J., & Yamamoto, J. (2002). On the dynamics of robot exploration learning. Cognitive Systems Research, 3(3), 459-470.

ps.Z
PDF

Conference paper with peer-reviewed

C025. Tani, J. (2002). Articulation of sensory-motor experiences by ‘Forwarding Forward Model’: From robot experiments to phenomenology. Proc. 7th Int. Conf. on Simulation of Adaptive Behavior (SAB’02), pp. 171-180, Edinburgh, UK, August, edited by Hallam B., Floreano D., Hayes G., Meyer J., and Hallam J., The MIT Press.

PDF

C024. Tani, J. (2002). Self-organization of behavioral primitives as multiple attractor dynamics: a robot experiment. Proc. 2002 Int. Joint Conf. on Neural Networks (IJCNN’02), pp489-494, Honolulu, USA, May.

C023. Tani, J. (2002). The level organization by ‘Forwarding Forward models’: from robot experiments. Proc. 7th Int. Symp. on Artificial Life and Robotics (AROB7th’02), pp. 359-366, Beppu, Japan, January.

Others

O001. Sugita, Y., & Tani, J. (2002). A connectionist model which unifies the behavioral and the linguistic processes: Results from robot learning experiments. Mirror Neurons and the Evolution of Brain and Language, Delmenhorst, Germany, edited by Stamenov M.I. and Gallese V., John Benjamins Publishing, 363-376.

ps.Z

2001

Journal paper

J012. Ikegami, T., & Tani, J. (2001). Chaotic itinerancy needs embodied cognition to explain memory dynamics. Behavioral and Brain Sciences, 24(5), 818-819.

1999

Journal papers

J011. Tani, J., & Nolfi, S. (1999). Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Proc. 5th Int. Conf. on Simulation of Adaptive Behavior, pp.270-279, (Eds) R. Pfeifer, B. Blumberg, J.A. Meyer, S.W. Wilson, MA: The MIT Press, The revised version is in Neural Networks, 12, 1131-1141.

ps.Z
PDF

J010. Nolfi, S., & Tani, J. (1999). Extracting regularities in space and time through a cascade of prediction of prediction networks: The case of a mobile robot navigating in a structured environment. Connection Science, 11(2), 125-148.

Conference paper with peer-reviewed

C022. Tani, J., & Sugita, Y. (1999). On the dynamics of robot exploration learning. Proc. 5th European Conf. on Artificial Life (ECAL99), pp. 279-288, Lausanne, Switzerland, September.

1998

Journal paper

J009. Tani, J. (1998). An interpretation of the ‘Self’ from the dynamical systems perspective: a constructivist approach. Journal of Consciousness Studies, 5(5/6), 516-542.

ps.Z

PDF

Conference paper with peer-reviewed

C021. Ito, M., & Tani, J. (1998). Dynamic adaptation of a neural-net based agent. Proc. 8th Int. Conf. on Artificial Neural Networks (ICANN’98), pp. 1151-1156, Skovde, Sweden, September.

C020. Horikawa, K., Asoh, H., & Tani, J. (1998). Emergence of experts modules for mobile robot navigation from a mixture of Elman networks. Proc. Int. Conf. on Neural Information Processing Systems.

C019. Sugita, Y., & Tani, J. (1998). Emergence of cooperative/competitive behavior in two robot’s game: plans or skills?. SAB’98 Workshop on Adaptive Behavior using dynamic recurrent neural nets, Zurich, Switzerland.

C018. Tani, J., & Nolfi, S. (1998). Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Proc. 5th Int. Conf. on Simulation of Adaptive Behavior (SAB’98), pp. 270-279, Zurich, Switzerland, August, edited by Pfeifer R., Blumberg B., Meyer J-A., Wilson S., The MIT Press.

1997

Journal papers

J008. Tani, J., & Nolfi, S. (1997). Self-organization of modules and their hierarchy in robot learning problems: A dynamical systems approach. System Analysis for Higher Brain Function Research Project News Letter, 2(4), 1-11.

PDF

J007. Tani, J., & Fukumura, N. (1997). Self-organizing internal representation in learning of navigation: a physical experiment by the mobile robot YAMABICO. Neural Networks, 10(1), 153-159.

PDF

Conference paper with peer-reviewed

C017. Tani, J. (1997). Visual attention and learning of a cognitive robot. Proc. 7th Int. Conf. on Artificial Neural Networks (ICANN’97), Special session on Adaptive Autonomous Agents, pp. 697-702, Lausanne, Switzerland.

C016. Tani, J., Yamamoto, J., & Nishi, H. (1997). Dynamical interactions between learning, visual attention, and behavior: an experiment with a vision-based mobile robot. Proc. 4th European Conf. on Artificial Life (ECAL97), pp. 309-317, Brighton, UK, July, edited by Husbands P. and Harvey I., The MIT Press.

PDF

1996

Journal paper

J006. Tani, J. (1996). Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Trans. on Syst. Man and Cybern. Part B-Cybernetics, 26(3), 421-436.

PDF

Conference paper with peer-reviewed

C015. Tani, J. (1996). A dynamical systems approach to represent cognition of robots: a view of the internal observer. AAAI Fall Symposium: Embodied Cognition and Action, TR FS-96-02, 123-128, Cambridge, USA.

C014. Tani, J. (1996). Does dynamics solve the symbol grounding problem of robots?. Proc. AISB’96 Workshop: Learning in Robots and Animals, Brighton, UK.

1995

Paper

J005. Tani, J., & Fukumura, N. (1995). Embedding a grammatical description in deterministic chaos: an experiment in recurrent neural learning. Biological Cybernetics, 72, 365-370.

ps.Z
PDF

Conference paper with peer-reviewed

C013. Tani, J., & Fukumura, N. (1995). A dynamical systems approach for a learnable autonomous robot. Advances in Neural Information Processing Systems 8 (NIPS’95), pp. 989-995, Denver, Colorado, November, edited by Touretzky S.D., Mozer C. M., Hasselmo E.M., The MIT Press.

PDF

C012. Tani, J. (1995). Self-organization of symbolic processes through interactions with the physical world. Proc. 14th Int. Joint Conf. on Artificial Intelligence (IJCAI’95), pp. 112-118, Montreal, Canada, August.

PDF

C011. Tani, J. (1995). Essential dynamical structure in learnable autonomous robots. Proc. 3rd European Conf. on Artificial Life (ECAL95), Granada, Spain, June, Springer-Verlag.

C010. Tani, J. (1995). Embedding symbolic process into deterministic chaos. Proc. Biologically Inspired Evolutionary Systems (BIES95), pp. 156-162, Tokyo, Japan.

C009. Tani, J. (1995). Dynamical systems approach in learnable autonomous robots. Proc. Information Integration Workshop, Beyond Divide and Conquer Strategy (IIW95), pp. 241-249.

1994

Journal papers

J004. Fukumura, N., & Tani, J. (1994). Learning in robotics. Learning goal-directed behaviour as dynamical system for sensory motor system. Journal of the Robotics Society of Japan, 13(1), 75-81.

J003. Tani, J., & Fukumura, N. (1994). Learning goal-directed sensory-based navigation of a mobile robot. Neural Networks, 7(3), 553-563.

Conference paper with peer-reviewed

C008. Tani, J. (1994). Experiment of Learning and Chaotic Planning of a Mobile Robot. Proc. 2nd Int. Conf. on Fuzzy Logic, Neural Nets and Soft Computing, Iizuka, Japan.

C007. Tani, J., & Fukumura, N. (1994). Embedding task-based behavior into internal sensory-based attractor dynamics in navigation of a mobile robot. Proc. 1994 IEEE/RSJ/GI Int. Conf. on Intelligent Robots and Systems (IROS’94), 2, 886-893, Munich, Germany.

1993

Conference paper with peer-reviewed

C006. Tani, J., & Fukumura, N. (1993). Learning task-based behavior as attractor dynamics: an experiment of autonomous mobile robot. Proc. Int. Symp. on Nonlinear Theory and Its Applications (NOLTA’93), 2, 431-434, Hawaii, USA.

C005. Tani, J., & Fukumura, N. (1993). Learning goal-directed navigation as attractor dynamics for a sensory motor system: an experiment by the mobile robot YAMABICO”. IEEE Proc. Int. Joint Conf. on Neural Networks (IJCNN’93), pp. 1747-1753, Nagoya, Japan.

1992

Journal papers

J002. Tani, J. (1992). Proposal of chaotic steepest descent method for neural networks and analysis of their dynamics. Electronics and Communications in Japan, Part 3, 75(4), 62-70.

J001. Tani, J., & Fujita, M. (1992). Coupling of memory search and mental rotation by a nonequilibrium dynamics neural network. IEICE Trans. Fundamentals, E75-A(5), 578-585.

Conference paper with peer-reviewed

C004. Tani, J. (1992). Diversity and regularity in chaotic wandering of robot. Proc. 2nd Int. Conf. on Fuzzy Logic and Neural Networks, pp. 127-132, Iizuka, Japan.

C003. Tani, J. (1992). The role of chaos in processing language. IEEE Proc. Int. Joint Conf. on Neural Networks (IJCNN’92), 3, 444-449, Baltimore, USA.

1989

Conference paper with peer-reviewed

C002. Tani, J., Hirobe, T., Niida, K., Koshijima, I., & Murakami, H. (1989). New learning algorithm for rule extraction by neural network and its application. Proceedings of the 4th Knowledge Acquisition for Knowledge-Based Systems Workshop, 1-6, 35.1-35.16, Banff, Alberta, October.

C001. Tani,J., & Yang,W.J. (1989). Numerical Simulation of Pipeline Control System. Proceeding of the 2nd ICFP, pp. 836-840, Zhejiang University, China.