Lecture

Non-Linear Dimensionality Reduction

Description

This lecture covers non-linear dimensionality reduction techniques, contrasting linear and non-linear mappings, exploring autoencoders, deep autoencoders, and convolutional autoencoders. It delves into the PyTorch implementation, 2D convolutional layers, and their applications in image retrieval, novel view synthesis, and body pose estimation. The lecture also discusses denoising autoencoders, contrastive autoencoders, and the importance of latent variables in direct estimation.

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.