Search Results for author: Jun Tani

Found 30 papers, 10 papers with code

Habits and goals in synergy: a variational Bayesian framework for behavior

1 code implementation11 Apr 2023 Dongqi Han, Kenji Doya, Dongsheng Li, Jun Tani

The habitual behavior is generated by using prior distribution of intention, which is goal-less; and the goal-directed behavior is generated by the posterior distribution of intention, which is conditioned on the goal.

Morphological Wobbling Can Help Robots Learn

1 code implementation5 May 2022 Fabien C. Y. Benureau, Jun Tani

We propose to make the physical characteristics of a robot oscillate while it learns to improve its behavioral performance.

Initialization of Latent Space Coordinates via Random Linear Projections for Learning Robotic Sensory-Motor Sequences

no code implementations26 Feb 2022 Vsevolod Nikulin, Jun Tani

Robot kinematics data, despite being a high dimensional process, is highly correlated, especially when considering motions grouped in certain primitives.

Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments

1 code implementation21 Feb 2022 Takazumi Matsumoto, Wataru Ohata, Fabien C. Y. Benureau, Jun Tani

We show that goal-directed action planning and generation in a teleological framework can be formulated using the free energy principle.

Active Inference in Robotics and Artificial Agents: Survey and Challenges

no code implementations3 Dec 2021 Pablo Lanillos, Cristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani

Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning.

Bayesian Inference

Emergence of sensory attenuation based upon the free-energy principle

1 code implementation4 Nov 2021 Hayato Idei, Wataru Ohata, Yuichi Yamashita, Tetsuya OGATA, Jun Tani

Consequently, shifts between the two sensorimotor contexts triggered transitions from one free-energy state to another in the network via executive control, which caused shifts between attenuating and amplifying prediction-error-induced responses in the sensory areas.

Goal-Directed Planning by Reinforcement Learning and Active Inference

no code implementations18 Jun 2021 Dongqi Han, Kenji Doya, Jun Tani

Habitual behavior, which is obtained from the prior distribution of ${z}$, is acquired by reinforcement learning.

Bayesian Inference Decision Making +2

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

no code implementations3 Mar 2021 Nadine Wirkuttis, Jun Tani

This study investigated how social interaction among robotic agents changes dynamically depending on the individual belief of action intention.

Learning Memory-Dependent Continuous Control from Demonstrations

no code implementations18 Feb 2021 Siqing Hou, Dongqi Han, Jun Tani

This paper builds on the idea of replaying demonstrations for memory-dependent continuous control, by proposing a novel algorithm, Recurrent Actor-Critic with Demonstration and Experience Replay (READER).

Continuous Control Decision Making +3

Morphological Development at the Evolutionary Timescale: Robotic Developmental Evolution

1 code implementation28 Oct 2020 Fabien C. Y. Benureau, Jun Tani

Evolution and development operate at different timescales; generations for the one, a lifetime for the other.

Developmental Learning

Towards hybrid primary intersubjectivity: a neural robotics library for human science

no code implementations29 Jun 2020 Hendry F. Chame, Ahmadreza Ahmadi, Jun Tani

Human-robot interaction is becoming an interesting area of research in cognitive science, notably, for the study of social cognition.

Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network

1 code implementation27 May 2020 Takazumi Matsumoto, Jun Tani

It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences.

Variational Recurrent Models for Solving Partially Observable Control Tasks

1 code implementation ICLR 2020 Dongqi Han, Kenji Doya, Jun Tani

In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve the task, and how to improve the policy.

Memorization Reinforcement Learning (RL)

Cognitive and motor compliance in intentional human-robot interaction

no code implementations5 Nov 2019 Hendry Ferreira Chame, Jun Tani

Embodiment and subjective experience in human-robot interaction are important aspects to consider when studying both natural cognition and adaptive robotics to human environments.

Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory

no code implementations12 Mar 2019 Minju Jung, Takazumi Matsumoto, Jun Tani

Furthermore, our analysis of comparative experiments indicated that introduction of visual working memory and the inference mechanism using variational Bayes predictive coding significantly improve the performance in planning adequate goal-directed actions.

Bayesian Inference

Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networks

1 code implementation29 Jan 2019 Dongqi Han, Kenji Doya, Jun Tani

Furthermore, we show that the self-developed compositionality of the network enhances faster re-learning when adapting to a new task that is a re-composition of previously learned sub-goals, than when starting from scratch.

Continuous Control Meta-Learning +1

A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition

1 code implementation4 Nov 2018 Ahmadreza Ahmadi, Jun Tani

The model introduces a weighting parameter, the meta-prior, to balance the optimization pressure placed on two terms of a lower bound on the marginal likelihood of the sequential data.

regression

Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization

1 code implementation28 May 2018 German I. Parisi, Jun Tani, Cornelius Weber, Stefan Wermter

Both growing networks can expand in response to novel sensory experience: the episodic memory learns fine-grained spatiotemporal representations of object instances in an unsupervised fashion while the semantic memory uses task-relevant signals to regulate structural plasticity levels and develop more compact representations from episodic experience.

Active Learning Continuous Object Recognition +1

A Dynamic Neural Network Approach to Generating Robot's Novel Actions: A Simulation Experiment

no code implementations15 May 2018 Jungsik Hwang, Jun Tani

The results also showed that the different way of learning the basic actions induced the self-organization of the memory structure with the different characteristics, resulting in the generation of different levels of creative actions.

Generating Goal-Directed Visuomotor Plans Based on Learning Using a Predictive Coding-type Deep Visuomotor Recurrent Neural Network Model

no code implementations7 Mar 2018 Minkyu Choi, Takazumi Matsumoto, Minju Jung, Jun Tani

The current paper presents how a predictive coding type deep recurrent neural networks can generate vision-based goal-directed plans based on prior learning experience by examining experiment results using a real arm robot.

Predictive Coding for Dynamic Visual Processing: Development of Functional Hierarchy in a Multiple Spatio-Temporal Scales RNN Model

no code implementations2 Aug 2017 Minkyu Choi, Jun Tani

The paper examines how model performance during pattern generation as well as predictive imitation varies depending on the stage of learning.

Bridging the Gap between Probabilistic and Deterministic Models: A Simulation Study on a Variational Bayes Predictive Coding Recurrent Neural Network Model

no code implementations30 Jun 2017 Ahmadreza Ahmadi, Jun Tani

We examined how this weighting can affect development of different types of information processing while learning fluctuated temporal patterns.

Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach

no code implementations8 Jun 2017 Jungsik Hwang, Jun Tani

This study investigates how adequate coordination among the different cognitive processes of a humanoid robot can be developed through end-to-end learning of direct perception of visuomotor stream.

Decision Making

Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning

no code implementations8 Jun 2017 Jungsik Hwang, Jinhyung Kim, Ahmadreza Ahmadi, Minkyu Choi, Jun Tani

This study presents a dynamic neural network model based on the predictive coding framework for perceiving and predicting the dynamic visuo-proprioceptive patterns.

Action Generation

Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition

no code implementations24 May 2017 Minju Jung, Haanvid Lee, Jun Tani

In this paper, inspired by the normalization and detrending methods, we propose adaptive detrending (AD) for temporal normalization in order to accelerate the training of ConvRNNs, especially for convolutional gated recurrent unit (ConvGRU).

Video Recognition

Predictive Coding for Dynamic Vision : Development of Functional Hierarchy in a Multiple Spatio-Temporal Scales RNN Model

no code implementations6 Jun 2016 Minkyu Choi, Jun Tani

The current paper presents a novel recurrent neural network model, the predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in the predictive coding framework.

Sensorimotor Input as a Language Generalisation Tool: A Neurorobotics Model for Generation and Generalisation of Noun-Verb Combinations with Sensorimotor Inputs

no code implementations11 May 2016 Junpei Zhong, Martin Peniak, Jun Tani, Tetsuya OGATA, Angelo Cangelosi

The paper presents a neurorobotics cognitive model to explain the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot.

Language Acquisition Sentence

Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks

no code implementations5 Feb 2016 Haanvid Lee, Minju Jung, Jun Tani

The analysis of the internal representation obtained through the learning with the dataset clarifies what sorts of functional hierarchy can be developed by extracting the essential compositionality underlying the dataset.

Achieving Synergy in Cognitive Behavior of Humanoids via Deep Learning of Dynamic Visuo-Motor-Attentional Coordination

no code implementations9 Jul 2015 Jungsik Hwang, Minju Jung, Naveen Madapana, Jinhyung Kim, Minkyu Choi, Jun Tani

The current study examines how adequate coordination among different cognitive processes including visual recognition, attention switching, action preparation and generation can be developed via learning of robots by introducing a novel model, the Visuo-Motor Deep Dynamic Neural Network (VMDNN).

Cannot find the paper you are looking for? You can Submit a new open access paper.