Loading Events

« All Events

  • This event has passed.
:

Dynamical System Perspective for Machine Learning

June 13 @ 4:00 pm - 5:00 pm KST

B378 Seminar room, IBS, 55 Expo-ro Yuseong-gu
Daejeon, 34126 Korea, Republic of
+ Google Map

Speaker

Ryeongkyung Yoon
The University of Utah
Abstract: The connection between deep neural networks and ordinary differential equations (ODEs) is an active field of research in machine learning. In this talk, we view the hidden states of a neural network as a continuous object governed by a dynamical system. The underlying vector field is written using a dictionary representation motivated by the equation discovery method. Within this framework, we develop models for two particular machine learning tasks: time-series classification and dimension reduction. We train the parameters in the models by minimizing a loss, which is defined using the solution to the governing ODE. To attain a regular vector field, we introduce a regularization term measuring the mean total kinetic energy of the flow, which is motivated by optimal transportation theory. We solve the optimization problem using a gradient-based method where the gradients are computed via the adjoint method from optimal control theory. Through various experiments on synthetic and real-world datasets, we demonstrate the performance of the proposed models. We also interpret the learned models by visualizing the phase plots of the underlying vector field and solution trajectories.  

 

Details

Date:
June 13
Time:
4:00 pm - 5:00 pm KST
Event Category:

Organizer

Jae Kyoung Kim
Email:
jaekkim@kaist.ac.kr

Venue

B378 Seminar room, IBS
55 Expo-ro Yuseong-gu
Daejeon, 34126 Korea, Republic of
+ Google Map
IBS 의생명수학그룹 Biomedical Mathematics Group
기초과학연구원 수리및계산과학연구단 의생명수학그룹
대전 유성구 엑스포로 55 (우) 34126
IBS Biomedical Mathematics Group (BIMAG)
Institute for Basic Science (IBS)
55 Expo-ro Yuseong-gu Daejeon 34126 South Korea
Copyright © IBS 2021. All rights reserved.