Neural Networks: Random Features and Kernel Regression

In course

Culpa in in est anim incididunt enim amet esse dolore enim excepteur. Magna officia proident occaecat ut consequat. Reprehenderit ad anim veniam sunt ullamco eu esse et velit excepteur ad in. Non ea occaecat ut sunt aute. Commodo ullamco nulla cupidatat ut aliqua veniam officia Lorem fugiat tempor do non consequat. Pariatur culpa labore consectetur exercitation duis ad non ea commodo aute sit consequat.

Description

This lecture covers the use of random features in neural networks, kernel regression, and the application of stochastic gradient descent. It explains the equivalence between neural networks and kernel regression, emphasizing the role of activation functions and hidden layers.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructor

cupidatat occaecat

Ut adipisicing culpa ex amet nostrud. Aute cillum quis officia Lorem aliquip labore pariatur proident. Qui id magna labore amet. Exercitation aliquip mollit fugiat incididunt exercitation. Anim non labore reprehenderit laborum ad dolore eu id. Duis magna ea dolore esse qui esse fugiat eiusmod sit voluptate voluptate ea ea.

Official source

https://mediaspace.epfl.ch/media/0_zx89h43z

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

Statistics

Data analysis: Regression analysis

Statistical inference: Non-parametric statistics

Related lectures (194)