3 papers
cs.LG2020
Residual Network Based Direct Synthesis of EM Structures: A Study on One-to-One Transformers
David Munzer, Siawpeng Er, Minshuo Chen +4
We propose using machine learning models for the direct synthesis of on-chip electromagnetic (EM) passive structures to enable rapid or even automated designs and optimizations of…
cs.LG2019
Towards Understanding the Importance of Noise in Training Neural Networks
Mo Zhou, Tianyi Liu, Yan Li +3
Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largel…
cs.LG2019
Inductive Bias of Gradient Descent based Adversarial Training on Separable Data
Yan Li, Ethan X. Fang, Huan Xu +1
Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unex…