Lecture

Lecture 8 (2024)

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)

Efficient Machine Learning via Data Summarization

Explores efficient machine learning through data summarization, covering challenges, methods, and impactful applications in various domains.

Document Analysis: Topic Modeling

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

Machine Learning: Supervised and Unsupervised Learning Techniques

Covers supervised and unsupervised learning techniques in machine learning, highlighting their applications in finance and environmental analysis.

Machine Learning for Solving PDEs: Random Feature Method

Explores the Random Feature Method for solving PDEs using machine learning algorithms to approximate high-dimensional functions efficiently.

Non-Conceptual Knowledge Systems

Delves into the impact of deep learning on non-conceptual knowledge systems and the advancements in transformers and generative adversarial networks.

Deep Learning III

Delves into deep learning optimization, challenges, SGD variants, critical points, overparametrized networks, and adaptive methods.

Polynomial Networks: Spectral Bias Analysis

Delves into the spectral bias of polynomial neural networks, analyzing the impact on learning different frequencies and discussing experimental results.

Deep Splines: Unifying Framework for Deep Neural Networks

Introduces a functional framework for deep neural networks with adaptive piecewise-linear splines, focusing on biomedical image reconstruction and the challenges of deep splines.

Universal Approximation Theorem: MLP

Covers Multi-Layer Perceptrons (MLP) and their application from classification to regression, including the Universal Approximation Theorem and challenges with gradients.

Introduction to Machine Learning

Covers the basics of machine learning, including supervised and unsupervised learning, linear regression, and classification.

Deep Learning: Generalization and Optimization

Delves into the challenges and benefits of deep learning, highlighting the transition to convolutional neural networks and the impact of network width on the loss landscape.

Deep Learning for Autonomous Vehicles: Learning

Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.

Neural Networks: Multi-layers

Explains the learning process in multi-layer neural networks, including back-propagation, activation functions, weights update, and error backpropagation.

Neural Networks: Training and Optimization

Explores the training and optimization of neural networks, addressing challenges like non-convex loss functions and local minima.

Dimensionality Reduction: PCA & Autoencoders

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

Structures in Non-Convex Optimization

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

Understanding Machine Learning: Exactly Solvable Models

Explores machine learning through solvable models, covering sample complexity, neural networks, and computational gaps.

Splines and Machine Learning

Explores supervised learning as an ill-posed problem and the integration of sparse adaptive splines into neural architectures.

Understanding Autoencoders

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

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.