Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Understanding Autoencoders

In course

CS-233(a): Introduction to machine learning (BA3)

Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented. ...

Description

This lecture covers the fundamentals of autoencoders, starting with linear mappings in Principal Component Analysis (PCA) and extending to nonlinear mappings in autoencoders. It explores deep autoencoders, denoising autoencoders, and sparse autoencoders, highlighting their applications in dimensionality reduction and data retrieval. The concept of kernel PCA is introduced for nonlinear data, along with convolutional autoencoders for image data. The lecture concludes with a demonstration of autoencoder applications and mappings.

Instructor

Mathieu Salzmann

I am a Senior Researcher at EPFL-CVLab, and, since May 2020, an Artificial Intelligence Engineer at ClearSpace (50%). Previously, I was a Senior Researcher and Research Leader in NICTA's computer vision research group. Prior to this, from Sept. 2010 to Jan 2012, I was a Research Assistant Professor at TTI-Chicago, and, from Feb. 2009 to Aug. 2010, a postdoctoral fellow at ICSI and EECS at UC Berkeley under the supervision of Prof. Trevor Darrell. I obtained my PhD in Jan. 2009 from EPFL under the supervision of Prof. Pascal Fua.

Official source

Related concepts (32)

Dimensionality reduction

Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension. Working in high-dimensional spaces can be undesirable for many reasons; raw data are often sparse as a consequence of the curse of dimensionality, and analyzing the data is usually computationally intractable (hard to control or deal with).

Nonlinear dimensionality reduction

Nonlinear dimensionality reduction, also known as manifold learning, refers to various related techniques that aim to project high-dimensional data onto lower-dimensional latent manifolds, with the goal of either visualizing the data in the low-dimensional space, or learning the mapping (either from the high-dimensional space to the low-dimensional embedding or vice versa) itself. The techniques described below can be understood as generalizations of linear decomposition methods used for dimensionality reduction, such as singular value decomposition and principal component analysis.

Autoencoder

An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction. Variants exist, aiming to force the learned representations to assume useful properties.

Kernel principal component analysis

In the field of multivariate statistics, kernel principal component analysis (kernel PCA) is an extension of principal component analysis (PCA) using techniques of kernel methods. Using a kernel, the originally linear operations of PCA are performed in a reproducing kernel Hilbert space. Recall that conventional PCA operates on zero-centered data; that is, where is one of the multivariate observations.

Variational autoencoder

In machine learning, a variational autoencoder (VAE) is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling. It is part of the families of probabilistic graphical models and variational Bayesian methods. Variational autoencoders are often associated with the autoencoder model because of its architectural affinity, but with significant differences in the goal and mathematical formulation. Variational autoencoders are probabilistic generative models that require neural networks as only a part of their overall structure.

Related lectures (58)

Principal Component Analysis: Dimensionality Reduction

Covers Principal Component Analysis for dimensionality reduction, exploring its applications, limitations, and importance of choosing the right components.

Unsupervised Learning: Dimensionality Reduction

Explores unsupervised learning techniques for reducing dimensions in data, emphasizing PCA, LDA, and Kernel PCA.

Landscape and Generalisation in Deep Learning

Explores the challenges and insights of deep learning, focusing on loss landscape, generalization, and feature learning.

Introduction to Machine Learning: Linear Models

Introduces linear models for supervised learning, covering overfitting, regularization, and kernels, with applications in machine learning tasks.

Dimensionality Reduction: PCA and Autoencoders