Lecture

The Problem of Overfitting

In course

Dolore amet velit nulla pariatur fugiat nostrud proident ipsum proident ex laboris. Lorem aliquip duis aute deserunt non. Quis mollit reprehenderit cillum amet excepteur irure id nisi Lorem sit quis. Duis officia elit magna irure dolore non. Aute do non ullamco do. Est adipisicing eu minim amet exercitation.

Description

This lecture covers the problem of overfitting in deep networks, using examples from classification and curve fitting. It discusses the flexibility of deep networks, the classification of new inputs, and the detour into polynomial curve fitting. The instructor emphasizes the importance of controlling flexibility to avoid overfitting.

Instructor

Exercitation mollit laboris dolor esse est ex culpa velit. In commodo ullamco mollit do ullamco qui aute duis quis consectetur aliquip fugiat consectetur deserunt. Eu laboris laborum laboris tempor cillum eu nostrud laboris aliquip in enim velit incididunt. Dolor ullamco duis sint laboris amet nostrud qui ullamco. Voluptate non qui aute ipsum proident est sunt excepteur exercitation esse. Consectetur eiusmod ex do tempor tempor commodo cupidatat ea ut. Dolore ea magna consectetur culpa.

Official source

https://mediaspace.epfl.ch/media/0_6qdgv80s

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

Statistics

Data analysis: Cross-validation

Related lectures (32)

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.