Lecture

Deep Learning: Overparameterization and Generalization

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 (64)

Deep Learning: Data Representations and Neural Networks

Covers data representations, Bag of Words, histograms, data pre-processing, and neural networks.

Convergence of Gradient Descent

Explores the convergence of gradient descent for strongly convex functions and the importance of regularization in preventing overfitting.

Deep Learning Fundamentals

Introduces deep learning fundamentals, covering data representations, neural networks, and convolutional neural networks.

Neural Networks: Basics and History

Covers the history and fundamental concepts of neural networks, including the mathematical model of a neuron, gradient descent, and the multilayer perceptron.

Introduction to Machine Learning

Provides an overview of Machine Learning, including historical context, key tasks, and real-world applications.

Deep Learning: Edge Detection and Neural Networks

Discusses edge detection techniques and the evolution of deep learning in neural networks.

Gradient Descent Methods for Artificial Neural Networks

Explores gradient descent methods for training artificial neural networks, covering supervised learning, single-layer networks, and modern gradient descent rules.

Provable and Generalizable Robustness in Deep Learning

Explores adversarial examples, defenses, and certifiable robustness in deep learning, including Gaussian smoothing and perceptual attacks.

Double Descent Curves: Overparametrization

Explores double descent curves and overparametrization in machine learning models, highlighting the risks and benefits.

Non-Conceptual Knowledge Systems: Style Transfer and Image Translation

Explores style transfer, image translation, self-supervised learning, video prediction, and image description generation using deep learning techniques.

Convolutional Neural Networks

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

Machine-learned force fields for molecular simulation

Explores machine-learned force fields for accurate molecular simulations and the solution of the electronic Schrödinger equation.

Dynamics of Linear Neural Networks

Explores the learning dynamics of deep neural networks using linear networks for analysis, covering two-layer and multi-layer networks, self-supervised learning, and benefits of decoupled initialization.

Deep Generative Models: Variational Autoencoders & GANs

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

Generalization in Deep Learning

Delves into the trade-off between model complexity and risk, generalization bounds, and the dangers of overfitting complex function classes.

Nearest Neighbor Rules: Part 2

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

Regularization Methods: Training and Validation Base

Explores regularization methods in neural networks, emphasizing the importance of training and validation bases to prevent overfitting.

Deep and Robust Reinforcement Learning Techniques

Discusses advanced reinforcement learning techniques, focusing on deep and robust methods, including actor-critic frameworks and adversarial learning strategies.

Document Analysis: Topic Modeling

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

Neural Word Embeddings: Learning Representations for Natural Language

Covers neural word embeddings and methods for learning word representations in natural language processing.