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

Concept

Variational autoencoder

Related lectures (31)

Generative Models: Self-Attention and Transformers

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

Evaluating Machine Accuracy and Robustness on ImageNet

Explores the evaluation of machine and human accuracy and robustness on ImageNet, highlighting progress, challenges, and the need for improvement.

Variational Auto-Encoders and NVIB

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

Dimensionality Reduction: PCA & Autoencoders

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

Dimensionality Reduction: PCA and Kernel PCA

Covers PCA, Kernel PCA, and autoencoders for dimensionality reduction in data analysis.

Non-Linear Dimensionality Reduction

Covers non-linear dimensionality reduction techniques using autoencoders, deep autoencoders, and convolutional autoencoders for various applications.

Understanding Autoencoders

Explores autoencoders, from linear mappings in PCA to nonlinear mappings, deep autoencoders, and their applications.

Encoder for Force and Vision in Manipulation

Explores combining force and vision for efficient manipulation tasks using a lower dimensional representation.

Stochastic Softmax Tricks

Explores stochastic softmax tricks, reparametrization, and argmax, addressing challenges in expectation estimation and gradient variance.

Generative Models: Boltzmann Machine

Covers generative models, focusing on Boltzmann machines and constrained maximization using Lagrange multipliers.

Optimal Weak Transport Barycenters: Computational Aspects

By Elsa Cazelles explores the computation of optimal weak transport barycenters and their practical applications.

Medical Image Reconstruction: From Model-Based to Data-Driven

Explores the evolution of medical image reconstruction techniques, from classical methods to data-driven approaches using deep neural networks.

The statistical view: generative models

Explores interpreting Neural Network output as a probability through statistical generative models.

Nearest Neighbor Rules: Part 2

Explores the Nearest Neighbor Rules, k-NN algorithm challenges, Bayes classifier, and k-means algorithm for clustering.

Non Conceptual Knowledge Systems

Explores non conceptual knowledge systems through image translation, video synthesis, self-supervised learning challenges, and universal representations.

Regularized Cross-Entropy Risk

Explores the regularized cross-entropy risk in neural networks, covering training processes and challenges in deep networks.

Splines and Imaging: From Compressed Sensing to Deep Neural Nets

Explores the optimality of splines for imaging and deep neural networks, demonstrating sparsity and global optimality with spline activations.

Variational Autoencoders Log in to Mediaspace to watch this video

Covers Variational Autoencoders, a probabilistic approach to autoencoders for data generation and feature representation, with applications in Natural Language Processing.

Deep Generative Models Log in to Mediaspace to watch this video

Covers deep generative models, including variational autoencoders, GANs, and deep convolutional GANs.

Document Analysis: Topic Modeling Log in to Mediaspace to watch this video

Explores document analysis, topic modeling, and generative models for data generation in machine learning.