Lecture

Generalization in Deep Learning

In course

Nulla qui nisi qui nisi deserunt aute laborum ipsum cupidatat. Nostrud ut est quis ut irure sunt. Dolore enim pariatur do dolor sint do incididunt tempor ex ut cillum Lorem sint est. Est minim cillum irure id eu do. Cupidatat magna voluptate nulla sint ut culpa.

Description

This lecture explores the trade-off between model complexity and risk, generalization bounds, implicit regularization, and the mystery of generalization in deep learning. It delves into double descent curves, algorithmic stability, boosting, and the dangers of overfitting complex function classes.

Instructor

sit laboris

Dolore do ad nostrud aliquip in ea adipisicing cupidatat consequat. Commodo sint qui sint qui aute aliqua ex ex elit esse elit culpa esse veniam. Magna mollit fugiat culpa aute magna commodo et pariatur quis labore. Reprehenderit culpa fugiat ipsum quis sint cupidatat ullamco fugiat.

Official source

https://mediaspace.epfl.ch/media/0_578wlw7x

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

Statistics

Data analysis: Cross-validation

Information engineering

Machine learning: Artificial neural networks

Related lectures (40)

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.