Search Results for author:
Found 16 papers, 3 papers with code
Magic for the Age of Quantized DNNs
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.
Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM
In this paper, we reveal the Bayesian generalization error in PCBM with a three-layered and linear architecture.
Can Transformers Predict Vibrations?
This resonance, caused by the interaction between motor and tire vibrations, puts excessive loads on the vehicle's drive shaft.
Convergences for Minimax Optimization Problems over Infinite-Dimensional Spaces Towards Stability in Adversarial Training
This instability problem comes from the difficulty of the minimax optimization, and there have been various approaches in GANs and UDAs to overcome this problem.
Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks
Our proposed method can solve these problems; namely, SAF can halve the number of operations during the forward process, and it can be theoretically proven that SAF is consistent with the Spike Representation and OTTT, respectively.
Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulation
However, it has not yet been possible to understand the behavior of the generalization error in CBM since a neural network is a singular statistical model in general.
Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks
Spiking neural networks (SNNs) are energy-efficient neural networks because of their spiking nature.
C-SENN: Contrastive Self-Explaining Neural Network
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.
Rethinking the role of normalization and residual blocks for spiking neural networks
Biologically inspired spiking neural networks (SNNs) are widely used to realize ultralow-power energy consumption.
Concept Bottleneck Model with Additional Unsupervised Concepts
We refer to the proposed model as the concept bottleneck model with additional unsupervised concepts (CBM-AUC).
S$^3$NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks
To solve these problems, we propose a single-step spiking neural network (S$^3$NN), an energy-efficient neural network with low computational cost and high precision.
Study of Deep Generative Models for Inorganic Chemical Compositions
Generative models based on generative adversarial networks (GANs) and variational autoencoders (VAEs) have been widely studied in the fields of image generation, speech generation, and drug discovery, but, only a few studies have focused on the generation of inorganic materials.
Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
We present a method to encode and decode the position of atoms in 3-D molecules from a dataset of nearly 50, 000 stable crystal unit cells that vary from containing 1 to over 100 atoms.
Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World
We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world.
All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
One of the conventional methods for solving this problem is transfer learning for DNNs.
Accurate and Robust Registration of Nonrigid Surface Using Hierarchical Statistical Shape Model
In this paper, we propose a new non-rigid robust registration method that registers a point distribution model (PDM) of a surface to given 3D images.
