Skip to main content
Yann LeCun's Deep Learning Course at CDS
Purpose of the collection

This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. The prerequisites include: introduction to data science or a graduate-level machine learning course.

Courses in this collection
1
This module provides an introduction to the motivation of deep learning and its history and inspiration. The module covers the concepts of: gradient…
2
This course covers the concepts of recurrent and convolutional nets (theory and practice), natural signals properties and the convolution, and…
3
This module is intended to provide a foundation in energy-based models, and is a part of the Deep Learning Course at NYU's Center for Data Science, a…
4
This module is intended to provide a foundation in energy-based models. It is a part of the Deep Learning Course at NYU's Center for Data Science. …
5
This module covers the concept of associative memories in deep learning. It is a part of the Deep Learning Course at NYU's Center for Data Science. …
6
This module provides an introduction to the problem of speech recognition using neural models, emphasizing the CTC loss for training and inference…
7
This module covers the concepts of model predictive control, emulation of the kinematics from observations, training a policy, and predictive policy…
8
This module covers the concepts of gradient descent, stochastic gradient descent, and momentum. It is a part of the Deep Learning Course at NYU's…