25 citations · 59 across the 15 of their papers we have counts for
15 papers
Magic for the Age of Quantized DNNs
Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake
Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Mode…
Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM
Naoki Hayashi, Yoshihide Sawada
Concept Bottleneck Model (CBM) is a methods for explaining neural networks. In CBM, concepts which correspond to reasons of outputs are inserted in the last intermediate layer as o…
Can Transformers Predict Vibrations?
Fusataka Kuniyoshi, Yoshihide Sawada
Highly accurate time-series vibration prediction is an important research issue for electric vehicles (EVs). EVs often experience vibrations when driving on rough terrains, known a…
Convergences for Minimax Optimization Problems over Infinite-Dimensional Spaces Towards Stability in Adversarial Training
Takashi Furuya, Satoshi Okuda, Kazuma Suetake +1
Training neural networks that require adversarial optimization, such as generative adversarial networks (GANs) and unsupervised domain adaptations (UDAs), suffers from instability.…
Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks
Ryuji Saiin, Tomoya Shirakawa, Sota Yoshihara +2
In this article, we propose a new paradigm for training spiking neural networks (SNNs), spike accumulation forwarding (SAF). It is known that SNNs are energy-efficient but difficul…
Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulation
Naoki Hayashi, Yoshihide Sawada
Concept bottleneck model (CBM) is a ubiquitous method that can interpret neural networks using concepts. In CBM, concepts are inserted between the output layer and the last interme…
Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks
Kazuma Suetake, Takuya Ushimaru, Ryuji Saiin +1
Spiking neural networks (SNNs) are energy-efficient neural networks because of their spiking nature. However, as the spike firing rate of SNNs increases, the energy consumption doe…
C-SENN: Contrastive Self-Explaining Neural Network
Yoshihide Sawada, Keigo Nakamura
In this study, we use a self-explaining neural network (SENN), which learns unsupervised concepts, to acquire concepts that are easy for people to understand automatically. In conc…
Rethinking the role of normalization and residual blocks for spiking neural networks
Shin-ichi Ikegawa, Ryuji Saiin, Yoshihide Sawada +1
Biologically inspired spiking neural networks (SNNs) are widely used to realize ultralow-power energy consumption. However, deep SNNs are not easy to train due to the excessive fir…
Concept Bottleneck Model with Additional Unsupervised Concepts
Yoshihide Sawada, Keigo Nakamura
With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approach…
SNN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks
Kazuma Suetake, Shin-ichi Ikegawa, Ryuji Saiin +1
As the scales of neural networks increase, techniques that enable them to run with low computational cost and energy efficiency are required. From such demands, various efficient n…
Study of Deep Generative Models for Inorganic Chemical Compositions
Yoshihide Sawada, Koji Morikawa, Mikiya Fujii
Generative models based on generative adversarial networks (GANs) and variational autoencoders (VAEs) have been widely studied in the fields of image generation, speech generation,…
Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
Jordan Hoffmann, Louis Maestrati, Yoshihide Sawada +3
Generative models have achieved impressive results in many domains including image and text generation. In the natural sciences, generative models have led to rapid progress in aut…
Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World
Yoshihide Sawada
We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is import…
All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
Yoshihide Sawada, Yoshikuni Sato, Toru Nakada +2
In this article, we propose a transfer learning method for deep neural networks (DNNs). Deep learning has been widely used in many applications. However, applying deep learning is…