Search Results for author: Kookjin Lee

Found 22 papers, 4 papers with code

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

no code implementations20 Feb 2024 Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, Noseong Park

Extensively evaluating methods with seven image recognition benchmarks, we show that the proposed PAC-FNO improves the performance of existing baseline models on images with various resolutions by up to 77. 1% and various types of natural variations in the images at inference.

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

no code implementations19 Dec 2023 Youn-Yeol Yu, Jeongwhan Choi, Woojin Cho, Kookjin Lee, Nayong Kim, Kiseok Chang, ChangSeung Woo, Ilho Kim, SeokWoo Lee, Joon Young Yang, Sooyoung Yoon, Noseong Park

Recently, many mesh-based graph neural network (GNN) models have been proposed for modeling complex high-dimensional physical systems.

Operator-learning-inspired Modeling of Neural Ordinary Differential Equations

no code implementations16 Dec 2023 Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park

Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field.

Image Classification Image Generation +3

Graph Convolutions Enrich the Self-Attention in Transformers!

no code implementations7 Dec 2023 Jeongwhan Choi, Hyowon Wi, Jayoung Kim, Yehjin Shin, Kookjin Lee, Nathaniel Trask, Noseong Park

Transformers, renowned for their self-attention mechanism, have achieved state-of-the-art performance across various tasks in natural language processing, computer vision, time-series modeling, etc.

Code Classification speech-recognition +2

Reversible and irreversible bracket-based dynamics for deep graph neural networks

1 code implementation NeurIPS 2023 Anthony Gruber, Kookjin Lee, Nathaniel Trask

Recent works have shown that physics-inspired architectures allow the training of deep graph neural networks (GNNs) without oversmoothing.

Time Series Forecasting with Hypernetworks Generating Parameters in Advance

no code implementations22 Nov 2022 Jaehoon Lee, Chan Kim, Gyumin Lee, Haksoo Lim, Jeongwhan Choi, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park

Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i. e. time series are under temporal drifts).

Time Series Time Series Forecasting

Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting

no code implementations10 Oct 2022 Fan Wu, Sanghyun Hong, Donsub Rim, Noseong Park, Kookjin Lee

However, parameterization of dynamics using a neural network makes it difficult for humans to identify causal structures in the data.

Time Series Time Series Analysis

Parameter-varying neural ordinary differential equations with partition-of-unity networks

no code implementations1 Oct 2022 Kookjin Lee, Nathaniel Trask

In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture.

Unity

AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation

1 code implementation13 Jul 2022 Suneghyeon Cho, Sanghyun Hong, Kookjin Lee, Noseong Park

In this work, we propose adaptive momentum estimation neural ODEs (AdamNODEs) that adaptively control the acceleration of the classical momentum-based approach.

Computational Efficiency

Unsupervised physics-informed disentanglement of multimodal data for high-throughput scientific discovery

no code implementations7 Feb 2022 Nathaniel Trask, Carianne Martinez, Kookjin Lee, Brad Boyce

We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing.

Disentanglement Variational Inference

Climate Modeling with Neural Diffusion Equations

2 code implementations11 Nov 2021 Jeehyun Hwang, Jeongwhan Choi, Hwangyong Choi, Kookjin Lee, Dongeun Lee, Noseong Park

On the other hand, neural ordinary differential equations (NODEs) are to learn a latent governing equation of ODE from data.

Weather Forecasting

Regularizing Image Classification Neural Networks with Partial Differential Equations

no code implementations29 Sep 2021 Jungeun Kim, Seunghyun Hwang, Jeehyun Hwang, Kookjin Lee, Dongeun Lee, Noseong Park

In other words, the knowledge contained by the learned governing equation can be injected into the neural network which approximates the PDE solution function.

Classification Image Classification

Structure-preserving Sparse Identification of Nonlinear Dynamics for Data-driven Modeling

no code implementations11 Sep 2021 Kookjin Lee, Nathaniel Trask, Panos Stinis

Discovery of dynamical systems from data forms the foundation for data-driven modeling and recently, structure-preserving geometric perspectives have been shown to provide improved forecasting, stability, and physical realizability guarantees.

Probabilistic partition of unity networks: clustering based deep approximation

no code implementations7 Jul 2021 Nat Trask, Mamikon Gulian, Andy Huang, Kookjin Lee

We enrich POU-Nets with a Gaussian noise model to obtain a probabilistic generalization amenable to gradient-based minimization of a maximum likelihood loss.

Clustering Probabilistic Deep Learning +2

Machine learning structure preserving brackets for forecasting irreversible processes

no code implementations NeurIPS 2021 Kookjin Lee, Nathaniel A. Trask, Panos Stinis

Forecasting of time-series data requires imposition of inductive biases to obtain predictive extrapolation, and recent works have imposed Hamiltonian/Lagrangian form to preserve structure for systems with reversible dynamics.

BIG-bench Machine Learning Time Series +1

Partition of unity networks: deep hp-approximation

no code implementations27 Jan 2021 Kookjin Lee, Nathaniel A. Trask, Ravi G. Patel, Mamikon A. Gulian, Eric C. Cyr

Approximation theorists have established best-in-class optimal approximation rates of deep neural networks by utilizing their ability to simultaneously emulate partitions of unity and monomials.

Unity

Neural Partial Differential Equations

no code implementations1 Jan 2021 Jungeun Kim, Seunghyun Hwang, Jihyun Hwang, Kookjin Lee, Dongeun Lee, Noseong Park

Neural ordinary differential equations (neural ODEs) introduced an approach to approximate a neural network as a system of ODEs after considering its layer as a continuous variable and discretizing its hidden dimension.

DPM: A Novel Training Method for Physics-Informed Neural Networks in Extrapolation

1 code implementation4 Dec 2020 Jungeun Kim, Kookjin Lee, Dongeun Lee, Sheo Yon Jin, Noseong Park

We present a method for learning dynamics of complex physical processes described by time-dependent nonlinear partial differential equations (PDEs).

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

no code implementations28 Oct 2020 Kookjin Lee, Eric J. Parish

This work proposes an extension of neural ordinary differential equations (NODEs) by introducing an additional set of ODE input parameters to NODEs.

Deep Conservation: A latent dynamics model for exact satisfaction of physical conservation laws

no code implementations21 Sep 2019 Kookjin Lee, Kevin Carlberg

In contrast to existing methods for latent dynamics learning, this is the only method that both employs a nonlinear embedding and computes dynamics for the latent state that guarantee the satisfaction of prescribed physical properties.

Computational Physics

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