UvA Deep Learning Course

About

Deep learning is primarily a study of multi-layered neural networks, spanning over a great range of model architectures. This course is taught in the MSc program in Artificial Intelligence of the University of Amsterdam. In this course we study the theory of deep learning, namely of modern, multi-layered neural networks trained on big data. The course focuses particularly on computer vision and language modelling, which are perhaps two of the most recognizable and impressive applications of the deep learning theory. The course is taught by Assistant Professor Efstratios Gavves, Kirill Gavrilyuk, Berkay Kicanaoglu, and Patrick Putzky.

News

The Practical 3 is released. Check Practical 3.
The Practical 2 is released. Check Practical 2.
The video links for the recordings of lectures 3, 4 are now available.
The slides from Lecture 4 are uploaded.
The slides from the SURF SARA presentation are uploaded.
The papers for the student presentatiins are uploaded, check Practical 4.

Lectures

Lecture 1

Introduction to Deep Learning and Neural Networks

Lecture 2

Learning with neural networks

Lecture 3

Deeper into Deep Learning
and Optimizations

Lecture 4

Convolutional Neural Networks
for Computer Vision

Lecture 5

Understanding ConvNets
and Knowledge Transfer

Lecture 6

Structured Prediction
with Convnets

Lecture 7

Language Models and
Word Embeddings

Lecture 8

Recurrent Neural Networks

Lecture 9

Unsupervised, Generative
and Adversarial Networks

Lecture 10

Invited talks by T. Kipf
R. Tao, Z. Li, P. Putzky

Lecture 11

Memory Networks for
Language Understanding

Lecture 12

Student presentations
Series 2

Lecture 13

Student presentations
Series 1

Lecture 14

Exotic Deep Learning

Lecture 15

SURF SARA Tutorial,
HPC Deep Learning

Hot Questions

During the course several interesting questions pop up. Instead of having them lost during the lectures, we put here all the questions could be of interest to more people, inside and outside the University of Amsterdam. Although not all questions are going to be immediately answered because of time constraints, the goal is to have the answers online as soon as possible. If you have an interesting question for which you would like an answer, you can always email us.

Hot questions

Course links

Some useful links for the course are the following:

Piazza website, wherere you can discuss with other students, see notifications and get in contact with your fellow classmates and the instructors.
Practicals repo , where you can download the practicals assignments for the course. As the course has freshly started, not all material is already there. Please download the next assignment whenever indicated by your instructors.
And of course, this is the website itself

Readings & other links

These are some other materials related to this course, machine learning and applied math in general. The first group is suggested readings that could help you with this course. The second group refers to links with similar courses on Deep Learning. The material taught in the UvA Deep Learning Course are partly inspired by the sources below. These lists are (hopefully) going to be updated regularly.

Readings

Deep Learning, a book written by I. Goodfellow, Y. Bengio and A. Courville.

Similar courses

Deep Learning, a course organized by Y. LeCun at the New York University.
Deep Learning for Natural Language Processing, a course organized by R. Socher at Stanford.
Convolutional Neural Networks for Visual Recognition, a course organized by A. Karpathy and Fei-Fei Li at Stanford.
Machine Learning, a course organized by N. de Freitas at Oxford.
Neural Networks for Machine Learning, a course organized by G. Hinton at Coursera.
Neural Networks, a course organized by H. Larochelle at Université de Sherbrooke.
Deep Learning, a course organized by Google at Udacity.
Topics Course on Deep Learning, a course organized by Joan Bruna at the Statistics Department of UC Berkeley.

Contact us!

If you have any questions or recommendations for the website or the course, you can always drop us a line! The knowledge should be free, so feel also free to use any of the material provided here (but please be so kind to cite us). In case you are a course instuctor and you want the solutions, please send us an email.

Room C3.229, Science Park 904 1098 XH, Amsterdam, The Netherlands

uva.deeplearning@gmail.com

UVA Deep Learning Course