Search Results for author: Yasuo Kuniyoshi

Found 18 papers, 0 papers with code

Assessing the Aesthetic Evaluation Capabilities of GPT-4 with Vision: Insights from Group and Individual Assessments

no code implementations6 Mar 2024 Yoshia Abe, Tatsuya Daikoku, Yasuo Kuniyoshi

Recently, it has been recognized that large language models demonstrate high performance on various intellectual tasks.

Language Modelling

Multi-task real-robot data with gaze attention for dual-arm fine manipulation

no code implementations15 Jan 2024 Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Additionally, this dataset includes visual attention signals as well as dual-action labels, a signal that separates actions into a robust reaching trajectory and precise interaction with objects, and language instructions to achieve robust and precise object manipulation.

Imitation Learning Object +1

Formulation of downward causation in the brain: whole beats its parts

no code implementations16 Oct 2023 Yoshiyuki Ohmura, Yasuo Kuniyoshi

A configurational force is a novel force of a certain type of aggregates not generated by a pair of elementary particles.

Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning

no code implementations5 Oct 2023 Takayuki Komatsu, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Based on this result, we hypothesize that it is important to maximize the attention mask of the image region best represented by a single latent vector corresponding to the attention mask.

Object Representation Learning +2

An algebraic theory to discriminate qualia in the brain

no code implementations31 May 2023 Yoshiyuki Ohmura, Wataru Shimaya, Yasuo Kuniyoshi

In addition, we show that a brain model that learns to satisfy the algebraic independence between neural networks separates the latent space into multiple metric spaces corresponding to qualia types, suggesting that our theory can contribute to the further development of the mathematical theory of consciousness.

Representation Learning

Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation

no code implementations18 Mar 2022 Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Long-horizon dexterous robot manipulation of deformable objects, such as banana peeling, is a problematic task because of the difficulties in object modeling and a lack of knowledge about stable and dexterous manipulation skills.

Imitation Learning Object +1

Memory-based gaze prediction in deep imitation learning for robot manipulation

no code implementations10 Feb 2022 Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

We propose that gaze prediction from sequential visual input enables the robot to perform a manipulation task that requires memory.

Gaze Estimation Gaze Prediction +2

Transformer-based deep imitation learning for dual-arm robot manipulation

no code implementations1 Aug 2021 Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior.

Imitation Learning Robot Manipulation

Reinforced Imitation Learning by Free Energy Principle

no code implementations25 Jul 2021 Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings.

Imitation Learning Reinforcement Learning (RL)

Transient Chaos in BERT

no code implementations6 Jun 2021 Katsuma Inoue, Soh Ohara, Yasuo Kuniyoshi, Kohei Nakajima

A Lite BERT (ALBERT) is literally characterized as a lightweight version of BERT, in which the number of BERT parameters is reduced by repeatedly applying the same neural network called Transformer's encoder layer.

Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation

no code implementations2 Feb 2021 Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

The results of this study demonstrate that a deep imitation learning based method, inspired by the gaze-based dual resolution visuomotor control system in humans, can solve the needle threading task.

Computational Efficiency Imitation Learning +1

Combining Imitation and Reinforcement Learning with Free Energy Principle

no code implementations1 Jan 2021 Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

Imitation Learning (IL) and Reinforcement Learning (RL) from high dimensional sensory inputs are often introduced as separate problems, but a more realistic problem setting is how to merge the techniques so that the agent can reduce exploration costs by partially imitating experts at the same time it maximizes its return.

Imitation Learning reinforcement-learning +1

Identifying Critical States by the Action-Based Variance of Expected Return

no code implementations26 Aug 2020 Izumi Karino, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Our results also demonstrate that the identified critical states are intuitively interpretable regarding the crucial nature of the action selection.

Reinforcement Learning (RL)

Graphical Gaussian Vector for Image Categorization

no code implementations NeurIPS 2012 Tatsuya Harada, Yasuo Kuniyoshi

This paper proposes a novel image representation called a Graphical Gaussian Vector, which is a counterpart of the codebook and local feature matching approaches.

Image Categorization Object Recognition

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