Explore the fundamentals of autoencoders in this 39-minute lecture, covering key concepts such as compression, linear auto encoders, principal component analysis, deep autoencoders, sparse representations, and denoising techniques. Gain insights into the architecture and applications of these powerful neural network models used for unsupervised learning and dimensionality reduction.
Overview
Syllabus
Introduction
Compression
Linear Auto Encoder
Principal Component Analysis
Autoencoders
Deep Autoencoders
Sparse representations
Denoising
Taught by
Pascal Poupart
