Lecture

24.05.2024 - Rémi Gribonval: Frugality in machine learning: sparsity, a value for the future?

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.

Related lectures (62)

Deep Generative Models: Part 2

Explores deep generative models, including mixtures of multinomials, PCA, deep autoencoders, convolutional autoencoders, and GANs.

Understanding Machine Learning: Exactly Solvable Models

Explores the statistical mechanics of learning, focusing on neural networks' mysteries and computational challenges.

Convolutional Neural Networks: Fundamentals

Covers the basics of Convolutional Neural Networks, including training optimization, layer structure, and potential pitfalls of summary statistics.

Loss Landscape: Minima and Saddle Points

Discusses minima in error functions, multiple minima, saddle points, weight space symmetry, and near-equivalent good solutions in deep neural networks.

Deep Learning: Data Representations and Neural Networks

Explores data representations, histograms, neural networks, and deep learning concepts.

Adaptive Gradient Methods: Theory and Applications

Explores adaptive gradient methods, their properties, convergence, and comparison with traditional optimization algorithms.

Improving Models of the Ventral Visual Pathway

Explores computational models of the ventral visual system, focusing on optimizing networks for real-world tasks and comparing to brain data.

Hand Pose Estimation

Covers hand pose estimation, regression techniques, and the evolution of image classification models from LeNet to VGG19.

Supervised Learning Overview

Covers CNNs, RNNs, SVMs, and supervised learning methods, emphasizing the importance of tuning regularization and making informed decisions in machine learning.

Non-Linear Dimensionality Reduction

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

Recurrent Neural Networks: Training and Challenges

Discusses recurrent neural networks, their training challenges, and solutions like LSTMs and GRUs.

Neural Network Training

Covers the training process of a neural network, including feedforward, cost function, gradient checking, and visualization of hidden layers.

Convolutional Neural Networks

Introduces Convolutional Neural Networks (CNNs) for autonomous vehicles, covering architecture, applications, and regularization techniques.

Neural Networks: Regularization & Optimization

Explores neural network regularization, optimization, and practical implementation tips.

Deep Neural Networks and Splines

Covers the fundamentals of deep neural networks and splines, exploring their properties, implications, and applications in modern machine learning.

Deep Learning: Data Representation and Multilayer Perceptron

Covers data representation, MLP training, activation functions, and gradient-based learning in deep neural networks.

Neural Networks Recap: Activation Functions

Covers the basics of neural networks, activation functions, training, image processing, CNNs, regularization, and dimensionality reduction methods.

Deep Neural Network Solution of the Electronic Schrödinger Equation

Explores deep neural network solutions for the electronic Schrödinger equation and their computational efficiency in many-body physics.

Deep Learning: Recurrent Neural Networks

Explores Recurrent Neural Networks for behavioral data, covering Deep Knowledge Tracing, LSTM, GRU networks, hyperparameter tuning, and time series prediction tasks.

Structures in Non-Convex Optimization

Covers non-convex optimization, deep learning training problems, stochastic gradient descent, adaptive methods, and neural network architectures.