3 papers
cs.SD2023
Bayesian inference and neural estimation of acoustic wave propagation
Yongchao Huang, Yuhang He, Hong Ge
In this work, we introduce a novel framework which combines physics and machine learning methods to analyse acoustic signals. Three methods are developed for this task: a Bayesian…
cs.LG2023
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
Wenlin Chen, Hong Ge
We introduce a novel approach for analyzing the training dynamics of ReLU networks by examining the characteristic activation boundaries of individual ReLU neurons. Our proposed an…
cs.LG2022
Understanding Sparse Feature Updates in Deep Networks using Iterative Linearisation
Adrian Goldwaser, Hong Ge
Larger and deeper networks generalise well despite their increased capacity to overfit. Understanding why this happens is theoretically and practically important. One recent approa…