Lecture

Careful Cross-validation

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)

Neural Networks: Multi-layers

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

Multilayer Neural Networks: Deep Learning

Covers the fundamentals of multilayer neural networks and deep learning.

Landscape and Generalisation in Deep Learning

Explores the challenges and insights of deep learning, focusing on loss landscape, generalization, and feature learning.

Deep Neural Networks: Optimization and Approximation

Explores optimization and approximation in deep neural networks, including optimal control and numerical experiments.

Numerical Encoding for DNN Accelerators

Explores novel numerical encoding for DNNs, optimizing accuracy and hardware efficiency, and multi-player information advantage.

Nonlinear ML Algorithms

Introduces nonlinear ML algorithms, covering nearest neighbor, k-NN, polynomial curve fitting, model complexity, overfitting, and regularization.

Understanding Machine Learning: Exactly Solvable Models

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

Deep Learning: Convolutional Neural Networks

Introduces Convolutional Neural Networks, explaining their architecture, training process, and applications in semantic segmentation tasks.

Model Selection: Evaluation and Generalization

Explores model selection, evaluation, and generalization in machine learning, emphasizing unbiased performance estimation and the risks of over-learning.

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.

Introduction to Neural Networks

Introduces neural networks, focusing on multilayer perceptrons and training with stochastic gradient descent.

Deep Learning: Convolutional Neural Networks

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

Quantifying Performance: Misclassification and F-Measure

Covers quantifying performance through true positives, false negatives, and false positives in machine learning.

Deep Learning: Convolutional Networks

Explores convolutional neural networks, backpropagation, and stochastic gradient descent in deep learning.

Reactive Molecules at Ultra-low Temperatures

Explores advanced techniques for studying reactive molecules at ultra-low temperatures, focusing on helium-solvated molecules and the challenges of simulating anharmonic cases.

Splines and Machine Learning

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

Transport Equation: Numerical Analysis

Covers optimization, control problems, and neural networks in the context of the transport equation.

Convolutional Neural Networks

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

Automatic Differentiation: BackProp revisited

Discusses automatic differentiation, emphasizing reverse mode differentiation for optimizing convolutional layer filters by gradient descent.

Statistical Physics of Learning

Offers insights into the statistical physics of learning, exploring the relationship between neural network structure and disordered systems.