no code implementations • 2 Jun 2023 • Tomohiro Hayase, Ryo Karakida
Multi-layer perceptron (MLP) is a fundamental component of deep learning that has been extensively employed for various problems.
no code implementations • 6 Oct 2022 • Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
In this study, we first reveal that a specific finite-difference computation, composed of both gradient ascent and descent steps, reduces the computational cost of GR.
no code implementations • 24 Mar 2021 • Benoit Collins, Tomohiro Hayase
Lastly, we can replace each weight with a Haar orthogonal random matrix independent of the Jacobian of the activation function using this key fact.
no code implementations • 26 Feb 2021 • Shohei Kubota, Hideaki Hayashi, Tomohiro Hayase, Seiichi Uchida
The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning.
no code implementations • 22 Dec 2020 • Tomohiro Hayase, Suguru Yasutomi, Takashi Katoh
Such forgetting is crucial also in a practical sense since the deployed DNNs may be trained on the data with outliers, poisoned by attackers, or with leaked/sensitive information.
no code implementations • 14 Jun 2020 • Tomohiro Hayase, Ryo Karakida
We investigate the spectral distribution of the conditional FIM, which is the FIM given a single sample, by focusing on fully-connected networks achieving dynamical isometry.
no code implementations • 11 Aug 2019 • Tomohiro Hayase
A well-conditioned Jacobian spectrum has a vital role in preventing exploding or vanishing gradients and speeding up learning of deep neural networks.
1 code implementation • 9 Apr 2018 • Tomohiro Hayase
The method is based on the spectral distribution instead of the traditional likelihood.