**Are you an EPFL student looking for a semester project?**

Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.

Lecture# Deep Learning: Convolutional Networks

Description

This lecture covers deep learning concepts related to convolutional neural networks, including the extension of multilayer perceptrons, autograd, stochastic gradient descent, convolutions, pooling, backpropagation, and the use of dynamic graphs for derivatives calculation. The instructor explains the forward propagation, backward propagation, and parameter derivatives calculation in deep networks. The lecture also discusses the challenges of writing complex models and the advantages of using libraries like PyTorch for automatic graph construction. Practical implementations of stochastic gradient descent and mini-batch processing are presented, along with the importance of shared parameters in deep learning models.

Login to watch the video

Official source

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

In course

Instructor

EE-311: Fundamentals of machine learning

Ce cours présente une vue générale des techniques d'apprentissage automatique, passant en revue les algorithmes, le formalisme théorique et les protocoles expérimentaux.

Related concepts (141)

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

Supervised learning

Supervised learning (SL) is a paradigm in machine learning where input objects (for example, a vector of predictor variables) and a desired output value (also known as human-labeled supervisory signal) train a model. The training data is processed, building a function that maps new data on expected output values. An optimal scenario will allow for the algorithm to correctly determine output values for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see inductive bias).

Support vector machine

In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data for classification and regression analysis. Developed at AT&T Bell Laboratories by Vladimir Vapnik with colleagues (Boser et al., 1992, Guyon et al., 1993, Cortes and Vapnik, 1995, Vapnik et al., 1997) SVMs are one of the most robust prediction methods, being based on statistical learning frameworks or VC theory proposed by Vapnik (1982, 1995) and Chervonenkis (1974).

Boosting (machine learning)

In machine learning, boosting is an ensemble meta-algorithm for primarily reducing bias, and also variance in supervised learning, and a family of machine learning algorithms that convert weak learners to strong ones. Boosting is based on the question posed by Kearns and Valiant (1988, 1989): "Can a set of weak learners create a single strong learner?" A weak learner is defined to be a classifier that is only slightly correlated with the true classification (it can label examples better than random guessing).

Generative adversarial network

A generative adversarial network (GAN) is a class of machine learning framework and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss. Given a training set, this technique learns to generate new data with the same statistics as the training set.

Related lectures (333)

Deep and Convolutional Networks: Generalization and Optimization

Explores deep and convolutional networks, covering generalization, optimization, and practical applications in machine learning.

Kernel Methods: Neural Networks

Covers the fundamentals of neural networks, focusing on RBF kernels and SVM.

Document Analysis: Topic Modeling

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

Deep Learning for Autonomous Vehicles: Learning

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

Machine Learning Fundamentals

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.