Tomohiro Hayase | DeepAI

AI Chat

Featured Co-authors

Seiichi Uchida
60 publications
Hideaki Hayashi
17 publications
Ryo Karakida
14 publications
Kazuki Osawa
9 publications
Takashi Katoh
4 publications
Benoît Collins
3 publications
Tomoumi Takase
2 publications
Suguru Yasutomi
1 publication
Shohei Kubota
1 publication

∙ 06/02/2023

MLP-Mixer as a Wide and Sparse MLP

Multi-layer perceptron (MLP) is a fundamental component of deep learning...

0 Tomohiro Hayase, et al. ∙

∙ 10/06/2022

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias

Gradient regularization (GR) is a method that penalizes the gradient nor...

0 Ryo Karakida, et al. ∙

∙ 03/24/2021

Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case

Free Probability Theory (FPT) provides rich knowledge for handling mathe...

0 Benoît Collins, et al. ∙

∙ 02/26/2021

Layer-Wise Interpretation of Deep Neural Networks Using Identity Initialization

The interpretability of neural networks (NNs) is a challenging but essen...

0 Shohei Kubota, et al. ∙

∙ 12/22/2020

Selective Forgetting of Deep Networks at a Finer Level than Samples

Selective forgetting or removing information from deep neural networks (...

0 Tomohiro Hayase, et al. ∙

∙ 06/14/2020

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry

The Fisher information matrix (FIM) is fundamental for understanding the...

0 Tomohiro Hayase, et al. ∙

∙ 08/11/2019

Almost Surely Asymptotic Freeness for Jacobian Spectrum of Deep Network

Free probability theory helps us to understand Jacobian spectrum of deep...

0 Tomohiro Hayase, et al. ∙

∙ 12/27/2018

Identifiability of parametric random matrix models

We investigate parameter identifiability of spectral distributions of ra...

0 Tomohiro Hayase, et al. ∙

∙ 04/09/2018

Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents

Based on free probability theory and stochastic optimization, we introdu...

0 Tomohiro Hayase, et al. ∙

∙ 10/25/2017

Free deterministic equivalent Z-scores of compound Wishart models: A goodness of fit test of 2DARMA models

We introduce a new method to qualify the goodness of fit parameter estim...

0 Tomohiro Hayase, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world