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: Part 2

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 deep generative models, including mixtures of multinomials and LDA for generating new documents, PCA for dimensionality reduction, deep autoencoders with nonlinear activation functions, convolutional autoencoders for image generation, and the training process using stochastic gradient descent. It also discusses using autoencoders as generative models, the need for defining distributions over latent variables, and the visual interpretation of VAE. The lecture concludes with a recap of GANs, conditional GANs, and the limitations of Bag of Words models.

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)

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

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).

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.

Residual neural network

A Residual Neural Network (a.k.a. Residual Network, ResNet) is a deep learning model in which the weight layers learn residual functions with reference to the layer inputs. A Residual Network is a network with skip connections that perform identity mappings, merged with the layer outputs by addition. It behaves like a Highway Network whose gates are opened through strongly positive bias weights. This enables deep learning models with tens or hundreds of layers to train easily and approach better accuracy when going deeper.

Related lectures (37)

Deep Learning: Convolutional Neural Networks

Covers Convolutional Neural Networks, standard architectures, training techniques, and adversarial examples in deep learning.

Convolutional Neural Networks

Covers Convolutional Neural Networks, including layers, training strategies, standard architectures, tasks like semantic segmentation, and deep learning tricks.

Dimensionality Reduction: PCA & Autoencoders

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

Generative Models: Self-Attention and Transformers

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