A5082353426- Neural dynamics and brain function
- Embodied and Extended Cognition
- Action Observation and Synchronization
- Robot Manipulation and Learning
- Gene Regulatory Network Analysis
- Neural Networks and Applications
- Free Will and Agency
- EEG and Brain-Computer Interfaces
- Single-cell and spatial transcriptomics
- Machine Learning and Algorithms
- Reinforcement Learning in Robotics
- Cognitive Science and Education Research
- Neural and Behavioral Psychology Studies
- Face Recognition and Perception
- Child and Animal Learning Development
- Psychology of Moral and Emotional Judgment
- Neuroethics, Human Enhancement, Biomedical Innovations
- Evolutionary Game Theory and Cooperation
- Additive Manufacturing and 3D Printing Technologies
- Machine Learning in Materials Science
- Functional Brain Connectivity Studies
- Domain Adaptation and Few-Shot Learning
Okinawa Institute of Science and Technology Graduate University
2020-2024
Active inference is a mathematical framework which originated in computational neuroscience as theory of how the brain implements action, perception and learning. Recently, it has been shown to be promising approach problems state-estimation control under uncertainty, well foundation for construction goal-driven behaviours robotics artificial agents general. Here, we review state-of-the-art implementations active state-estimation, control, planning learning; describing current achievements...
Abstract The brain attenuates its responses to self-produced exteroceptions (e.g., we cannot tickle ourselves). Is this phenomenon, known as sensory attenuation, enabled innately, or acquired through learning? Here, our simulation study using a multimodal hierarchical recurrent neural network model, based on variational free-energy minimization, shows that mechanism for attenuation can develop learning of two distinct types sensorimotor experience, involving externally produced...
This study explains how the leader-follower relationship and turn-taking could develop in a dyadic imitative interaction by conducting robotic simulation experiments based on free energy principle. Our prior showed that introducing parameter during model training phase can determine leader follower roles for subsequent interactions. The is defined as w, so-called meta-prior, weighting factor used to regulate complexity term versus accuracy when minimizing energy. be read sensory attenuation,...
We show that goal-directed action planning and generation in a teleological framework can be formulated by extending the active inference framework. The proposed model, which is built on variational recurrent neural network characterized three essential features. These are (1) goals specified for both static sensory states, e.g., goal images to reached dynamic processes, moving around an object, (2) model cannot only generate plans, but also understand through observation, (3) generates...
When agents interact socially with different intentions (or wills), conflicts are difficult to avoid. Although the means by which social can resolve such problems autonomously has not been determined, dynamic characteristics of agency may shed light on underlying mechanisms. Therefore, current study focused sense agency, a specific aspect referring congruence between agent's intention in acting and outcome, especially interaction contexts. Employing predictive coding active inference as...
This study investigated how a physical robot can adapt goal-directed actions in dynamically changing environments, real-time, using an active inference-based approach with incremental learning from human tutoring examples. Using our model, while good generalization be achieved appropriate parameters, when faced sudden, large changes the environment, may have to intervene correct of order reach goal, as caregiver might guide hands child performing unfamiliar task. In for learn tutor, we...
The current study investigated possible human-robot kinaesthetic interaction using a variational recurrent neural network model, called PV-RNN, which is based on the free energy principle. Our prior robotic studies PV-RNN showed that nature of interactions between top-down expectation and bottom-up inference strongly affected by parameter, meta-prior, regulates complexity term in energy.The also compares counter force generated when trained transitions are induced human experimenter...
The brain attenuates its responses to self-produced exteroceptions (e.g., we cannot tickle ourselves). Is this phenomenon, known as sensory attenuation, enabled innately, or acquired through learning? Here, our simulation study using a multimodal hierarchical recurrent neural network model, based on variational free-energy minimization, shows that mechanism for attenuation can develop learning of two distinct types sensorimotor experience, involving externally produced exteroceptions. For...