2 citations · 6 across the 16 of their papers we have counts for
5 papers · 1 filter
Generative Adversarial Networks via a Composite Annealing of Noise and Diffusion
Kensuke Nakamura, Simon Korman, Byung-Woo Hong
Generative adversarial network (GAN) is a framework for generating fake data using a set of real examples. However, GAN is unstable in the training stage. In order to stabilize GAN…
Regularization in network optimization via trimmed stochastic gradient descent with noisy label
Kensuke Nakamura, Bong-Soo Sohn, Kyoung-Jae Won +1
Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a…
Stochastic batch size for adaptive regularization in deep network optimization
Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive re…
Adaptive Regularization via Residual Smoothing in Deep Learning Optimization
Junghee Cho, Junseok Kwon, Byung-Woo Hong
We present an adaptive regularization algorithm that can be effectively applied to the optimization problem in deep learning framework. Our regularization algorithm aims to take in…
Adaptive Weight Decay for Deep Neural Networks
Kensuke Nakamura, Byung-Woo Hong
Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular re…