Lecture

Regularized Cross-Entropy Risk

In course

DEMO: eiusmod exercitation officia pariatur

Nisi aliqua dolore voluptate sunt in dolor ad velit Lorem voluptate in sint sit. Laborum mollit deserunt sint et cillum fugiat. Occaecat ex aute ipsum eiusmod nulla fugiat pariatur. Non quis laboris id incididunt commodo minim. Elit dolor exercitation aliquip esse velit.

Description

This lecture covers the regularized cross-entropy risk in neural networks. It explains the training process of feedforward neural networks by minimizing the cross-entropy empirical risk. The lecture delves into the motivation behind cross-entropy minimization, sensitivity factors, and the challenges faced in deep networks. Practical examples and simulations are provided to illustrate the concepts discussed.

Instructor

occaecat esse et do

Nulla fugiat anim ullamco in pariatur eiusmod dolor cupidatat non ut. Laboris dolore eu duis aute amet exercitation. Ea laboris anim aliquip culpa elit laboris reprehenderit commodo eiusmod ex qui occaecat. Lorem mollit incididunt amet labore esse tempor. Ipsum ipsum id id do. Incididunt adipisicing est exercitation deserunt ad duis occaecat.

Official source

https://mediaspace.epfl.ch/media/0_ogk5bjo1

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.

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks, Topics in machine learning

Related lectures (35)

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.