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

Lecture

Deep Generative Models

In course

DH-406: Machine learning for DH

This course aims to introduce the basic principles of machine learning in the context of the digital humanities. We will cover both supervised and unsupervised learning techniques, and study and implement methods to analyze diverse data types, such as imag ...

Description

This lecture covers the fundamentals of deep generative models, starting with a recap on document analysis and mixture of multinoullis. It then delves into Latent Dirichlet Allocation (LDA) and its generative model, discussing plate diagrams and learning methods. The lecture further explores variational inference for LDA, mean-field variational inference, and the training of autoencoders. It concludes with an introduction to variational autoencoders, their training process, and the challenges faced in training Generative Adversarial Networks (GANs). The lecture also touches on Deep Convolutional GANs (DCGANs) and other generative models like DALL-E 2.

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

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

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

Generative adversarial network

A generative adversarial network (GAN) is a class of machine learning framework and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss. Given a training set, this technique learns to generate new data with the same statistics as the training set.

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.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Variational Bayesian methods

Variational Bayesian methods are a family of techniques for approximating intractable integrals arising in Bayesian inference and machine learning. They are typically used in complex statistical models consisting of observed variables (usually termed "data") as well as unknown parameters and latent variables, with various sorts of relationships among the three types of random variables, as might be described by a graphical model. As typical in Bayesian inference, the parameters and latent variables are grouped together as "unobserved variables".

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 (36)

Generative Models: Self-Attention and Transformers

Covers generative models with a focus on self-attention and transformers, discussing sampling methods and empirical means.

Variational Auto-Encoders and NVIB

Explores Variational Auto-Encoders, Bayesian inference, attention-based latent spaces, and the effectiveness of Transformers in language processing.

Deep Learning Modus Operandi

Explores the benefits of deeper networks in deep learning and the importance of over-parameterization and generalization.

Dimensionality Reduction: PCA & Autoencoders

Explores PCA, Autoencoders, and their applications in dimensionality reduction and data generation.

Generative Models: Boltzmann Machine