TY - GEN
T1 - Robust Optimization Framework for Training Shallow Neural Networks Using Reachability Method
AU - Yang, Yejiang
AU - Xiang, Weiming
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data, the input training data is disturbed in the description of interval sets. Interval-based reachability analysis is then performed for the hidden layer. With the reachability analysis results, a robust optimization training method is developed in the framework of robust least-square problems. Then, the developed robust least-square problem is relaxed to a semi-definite programming problem. It has been shown that the developed robust learning method can provide better robustness against perturbations at the price of loss of training accuracy to some extent. At last, the proposed method is evaluated on a robot arm model learning example.
AB - In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data, the input training data is disturbed in the description of interval sets. Interval-based reachability analysis is then performed for the hidden layer. With the reachability analysis results, a robust optimization training method is developed in the framework of robust least-square problems. Then, the developed robust least-square problem is relaxed to a semi-definite programming problem. It has been shown that the developed robust learning method can provide better robustness against perturbations at the price of loss of training accuracy to some extent. At last, the proposed method is evaluated on a robot arm model learning example.
UR - http://www.scopus.com/inward/record.url?scp=85126021818&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126021818&partnerID=8YFLogxK
U2 - 10.1109/CDC45484.2021.9683106
DO - 10.1109/CDC45484.2021.9683106
M3 - Conference contribution
AN - SCOPUS:85126021818
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 3857
EP - 3862
BT - 60th IEEE Conference on Decision and Control, CDC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 60th IEEE Conference on Decision and Control, CDC 2021
Y2 - 13 December 2021 through 17 December 2021
ER -