Search Results for author: Byeongsu Sim

Found 7 papers, 1 papers with code

Magnitude and Angle Dynamics in Training Single ReLU Neurons

no code implementations27 Sep 2022 Sangmin Lee, Byeongsu Sim, Jong Chul Ye

To understand learning the dynamics of deep ReLU networks, we investigate the dynamic system of gradient flow $w(t)$ by decomposing it to magnitude $w(t)$ and angle $\phi(t):= \pi - \theta(t) $ components.

Improving Diffusion Models for Inverse Problems using Manifold Constraints

2 code implementations2 Jun 2022 Hyungjin Chung, Byeongsu Sim, Dohoon Ryu, Jong Chul Ye

Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process.

Colorization Image Inpainting

Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks

no code implementations11 Feb 2022 Sangmin Lee, Byeongsu Sim, Jong Chul Ye

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research.

Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN

no code implementations29 Aug 2020 Gyutaek Oh, Byeongsu Sim, Hyungjin Chung, Leonard Sunwoo, Jong Chul Ye

Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced runtime complexity.

Generative Adversarial Network

Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems

no code implementations25 Sep 2019 Byeongsu Sim, Gyutaek Oh, Jeongsol Kim, Chanyong Jung, Jong Chul Ye

To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance.

Computed Tomography (CT) Generative Adversarial Network +1

OPTIMAL TRANSPORT, CYCLEGAN, AND PENALIZED LS FOR UNSUPERVISED LEARNING IN INVERSE PROBLEMS

no code implementations25 Sep 2019 Byeongsu Sim, Gyutaek Oh, Sungjun Lim, and Jong Chul Ye

Specifically, we reveal that a cycleGAN architecture can be derived as a dual formulation of the optimal transport problem, if the PLS with a deep learning penalty is used as a transport cost between the two probability measures from measurements and unknown images.

Generative Adversarial Network

Cannot find the paper you are looking for? You can Submit a new open access paper.