Lecture

Generative Modeling: Then, Now and Tomorrow?

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture by the instructor covers the evolution of generative modeling, from traditional approaches to the latest advancements. It delves into topics such as gradient-domain metropolis light transport, deep convolutional reconstruction, GANs as a two-player game, and the challenges faced in training generative adversarial networks. The presentation also explores the concept of progressive growing of GANs for improved quality, stability, and variation in generated images, along with the importance of dataset distillation and the dissection of GANs. The lecture concludes with a vision for the future of generative models, emphasizing the potential for high-quality outputs with less data, improved generalization, and enhanced interpretability.

Official source

Related concepts (31)

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.

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.

Deep image prior

Deep image prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural network is randomly initialized and used as prior to solve inverse problems such as noise reduction, super-resolution, and inpainting. Image statistics are captured by the structure of a convolutional image generator rather than by any previously learned capabilities.

Deep belief network

In machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a class of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not between units within each layer. When trained on a set of examples without supervision, a DBN can learn to probabilistically reconstruct its inputs. The layers then act as feature detectors. After this learning step, a DBN can be further trained with supervision to perform classification.

Interpretability

In mathematical logic, interpretability is a relation between formal theories that expresses the possibility of interpreting or translating one into the other. Assume T and S are formal theories. Slightly simplified, T is said to be interpretable in S if and only if the language of T can be translated into the language of S in such a way that S proves the translation of every theorem of T. Of course, there are some natural conditions on admissible translations here, such as the necessity for a translation to preserve the logical structure of formulas.

Related lectures (64)

Deep Learning: Convolutional Neural Networks

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

Deep Generative Models: Variational Autoencoders & GANs

Explores Variational Autoencoders and Generative Adversarial Networks for deep generative modeling.

Deep Visual Recognition: Interpretability

Explores deep visual recognition, interpretability, CNN architectures, visual dictionaries, and attention mechanisms.

Machine Learning Fundamentals

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.

Generative Models: Trajectory Forecasting