199 citations · 528 across the 20 of their papers we have counts for
20 papers
Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision
Yuria Shimizu, Soh Takahashi, Takato Horii +1
Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models of human vision. Existing DN…
Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
Ken Takeda, Masafumi Oizumi, Ryo Karakida
Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem…
Koopman Mode Decomposition of Thermodynamic Dissipation in Nonlinear Langevin Dynamics
Daiki Sekizawa, Sosuke Ito, Masafumi Oizumi
Nonlinear oscillations are commonly observed in complex systems far from equilibrium, such as living organisms. These oscillations are essential for sustaining vital processes, lik…
Correspondence of high-dimensional emotion structures elicited by video clips between humans and Multimodal LLMs
Haruka Asanuma, Naoko Koide-Majima, Ken Nakamura +3
Recent studies have revealed that human emotions exhibit a high-dimensional, complex structure. A full capturing of this complexity requires new approaches, as conventional models…
Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment
Soh Takahashi, Masaru Sasaki, Ken Takeda +1
The learning mechanisms by which humans acquire internal representations of objects are not fully understood. Deep neural networks (DNNs) have emerged as a useful tool for investig…
Exploring internal representation of self-supervised networks: few-shot learning abilities and comparison with human semantics and recognition of objects
Asaki Kataoka, Yoshihiro Nagano, Masafumi Oizumi
Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do n…
Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence
Tadahiro Taniguchi, Masafumi Oizumi, Noburo Saji +2
This perspective paper explores the bidirectional influence between language emergence and the relational structure of subjective experiences, termed qualia structure, and lays out…
Decomposing Thermodynamic Dissipation of Linear Langevin Systems via Oscillatory Modes and Its Application to Neural Dynamics
Daiki Sekizawa, Sosuke Ito, Masafumi Oizumi
Recent developments in stochastic thermodynamics have elucidated various relations between the entropy production rate (thermodynamic dissipation) and the physical limits of inform…
Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models
Genji Kawakita, Ariel Zeleznikow-Johnston, Naotsugu Tsuchiya +1
Large Language Models (LLMs), such as the General Pre-trained Transformer (GPT), have shown remarkable performance in various cognitive tasks. However, it remains unclear whether t…
Fisher Information and Natural Gradient Learning of Random Deep Networks
Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for…
Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces
Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
Statistical neurodynamics studies macroscopic behaviors of randomly connected neural networks. We consider a deep layered feedforward network where input signals are processed laye…
Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Jun Kitazono, Ryota Kanai, Masafumi Oizumi
The ability to integrate information in the brain is considered to be an essential property for cognition and consciousness. Integrated Information Theory (IIT) hypothesizes that t…
Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem
Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
Two geometrical structures have been extensively studied for a manifold of probability distributions. One is based on the Fisher information metric, which is invariant under revers…
Geometry of Information Integration
Shun-ichi Amari, Naotsugu Tsuchiya, Masafumi Oizumi
Information geometry is used to quantify the amount of information integration within multiple terminals of a causal dynamical system. Integrated information quantifies how much in…
Fast and exact search for the partition with minimal information loss
Shohei Hidaka, Masafumi Oizumi
In analysis of multi-component complex systems, such as neural systems, identifying groups of units that share similar functionality will aid understanding of the underlying struct…
A unified framework for information integration based on information geometry
Masafumi Oizumi, Naotsugu Tsuchiya, Shun-ichi Amari
We propose a unified theoretical framework for quantifying spatio-temporal interactions in a stochastic dynamical system based on information geometry. In the proposed framework, t…
Measuring integrated information from the decoding perspective
Masafumi Oizumi, Shun-ichi Amari, Toru Yanagawa +2
Accumulating evidence indicates that the capacity to integrate information in the brain is a prerequisite for consciousness. Integrated Information Theory (IIT) of consciousness pr…
Influence of synaptic depression on memory storage capacity
Yosuke Otsubo, Kenji Nagata, Masafumi Oizumi +1
Synaptic efficacy between neurons is known to change within a short time scale dynamically. Neurophysiological experiments show that high-frequency presynaptic inputs decrease syna…
Instabilities in associative memory model with synaptic depression and switching phenomena among attractors
Yosuke Otsubo, Kenji Nagata, Masafumi Oizumi +1
We investigated how the stability of macroscopic states in the associative memory model is affected by synaptic depression. To this model, we applied the dynamical mean-field theor…
Mean Field Analysis of Stochastic Neural Network Models with Synaptic Depression
Yasuhiko Igarashi, Masafumi Oizumi, Masato Okada
We investigated the effects of synaptic depression on the macroscopic behavior of stochastic neural networks. Dynamical mean field equations were derived for such networks by takin…