Lecture

Weight Update: Mean Input and Bias Problem

Description

This lecture covers the weight update step in neural networks, focusing on the mean input shift and bias problem that arises with rectified linear units (ReLU) in hidden layers. It discusses the impact on weight updates, the problem for ReLU and other units with non-negative inputs, and the solution provided by Shifted Exponential Linear Units (SELU). The instructor emphasizes the importance of correct initialization to avoid vanishing gradient and linearity issues.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.