The Bias in learning theory
组织者
演讲者
时间
2023年06月12日 15:00 至 15:30
地点
数学系理科楼A-203
摘要
From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is therefore key to understanding robust generalisation. In this report, I will introduce the bias in some NNs, including the Group equivariant convolutional neural networks, diagonal linear networks, wide BNN and Optimisation in NN.