activity
20192022
most citedFinancial series prediction using Attention LSTM

16 citations · 22 across the 8 of their papers we have counts for

collaborators

9 papers

cs.LG20221 cited

Bounding the Rademacher Complexity of Fourier neural operators

Taeyoung Kim, Myungjoo Kang

A Fourier neural operator (FNO) is one of the physics-inspired machine learning methods. In particular, it is a neural operator. In recent times, several types of neural operators…

cs.LG20211 cited

Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models

Jaemoo Choi, Changyeon Yoon, Jeongwoo Bae +1

Out-of-distribution (OOD) detection is an important task in machine learning systems for ensuring their reliability and safety. Deep probabilistic generative models facilitate OOD…

cs.CV2021

High-Frequency aware Perceptual Image Enhancement

Hyungmin Roh, Myungjoo Kang

In this paper, we introduce a novel deep neural network suitable for multi-scale analysis and propose efficient model-agnostic methods that help the network extract information fro…

cs.LG2021

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

Sungkwon An, Jeonghoon Kim, Myungjoo Kang +2

Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, imag…

cs.CV2020

Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring

Sungkwon An, Hyungmin Roh, Myungjoo Kang

We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. Our model solves the deblurring problem by dividing it into two successi…

math.NA20201 cited

A second-order accurate semi-Lagrangian method for convection-diffusion equations with interfacial jumps

Hyuntae Cho, Yesom Park, Myungjoo Kang

In this paper, we present a second-order accurate finite-difference method for solving convectiondiffusion equations with interfacial jumps on a moving interface. The proposed meth…