Lecture

Interpretable Machine Learning: Sparse Decision Trees and Interpretable Neural Networks

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)

Understanding Machine Learning: Exactly Solvable Models

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

State Space Models: Expressivity and Transformers

Covers state space models and their expressivity compared to transformers, focusing on attention mechanisms and computational efficiency.

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.

Optical Computing: All-Analog Photoelectronic Chip for Vision Tasks

Presents an all-analog photoelectronic chip for high-speed vision tasks, addressing challenges in classical computation and proposing a hybrid optical-electrical framework.

Understanding Deep Learning

Explores deep learning fundamentals, including image classification, neural network working principles, and machine learning challenges.

Ensemble Methods: Random Forests

Covers ensemble methods like random forests and Gaussian Naive Bayes, explaining how they improve prediction accuracy and estimate conditional Gaussian distributions.

Convolutional Neural Networks

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

Digital Urban History: Lausanne Time Machine

Delves into digitizing historical documents, standardizing document structure, and applying neural networks for text recognition and image segmentation.

Neural Networks: Perceptron Model and Backpropagation Algorithm

Covers the perceptron model and backpropagation algorithm in neural networks.

Non conceptual knowledge systems

Explores the impact of Deep learning on Digital Humanities, focusing on non conceptual knowledge systems and recent advancements in AI.

The Hidden Convex Optimization Landscape of Deep Neural Networks

Explores the hidden convex optimization landscape of deep neural networks, showcasing the transition from non-convex to convex models.

State Space Models: Expressivity of Transformers

Covers state space models and the expressivity of transformers in sequence copying tasks.

Introduction to Machine Learning

Introduces fundamental machine learning concepts and algorithms for model training and evaluation.

Provable and Generalizable Robustness in Deep Learning

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

Deep Learning: Convolutional Neural Networks

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

Introduction to Machine Learning: Regression Fundamentals

Introduces the fundamentals of regression in machine learning, covering course logistics, key concepts, and the importance of loss functions in model evaluation.

Deep Learning

Covers the fundamentals of deep learning, including data representations, bag of words, data pre-processing, artificial neural networks, and convolutional neural networks.

Brain Intelligence: Continual Learning of Representational Models

Delves into the continual learning of representational models in brain intelligence, emphasizing rapid adaptation to unstructured environments.

Pavement Distress Detection

Covers the importance of preventive maintenance for pavement distress detection and introduces machine learning concepts for engineers.

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.