Summary

Since 2010 approaches in deep learning have revolutionized fields as diverse as computer vision, machine learning, or artificial intelligence. This course gives a systematic introduction into the main models of deep artificial neural networks: Supervised Learning and Reinforcement Learning.

Content

Keywords

Deep learning, artificial neural networks, reinforcement learning, TD learning, SARSA,

Learning Prerequisites

Required courses

CS 433 Machine Learning (or equivalent)

Calculus, Linear Algebra (at the level equivalent to first 2 years of EPFL in STI or IC, such as Computer Science, Physics or Electrical Engineering)

Recommended courses

stochastic processes

optimization

Important concepts to start the course

• Regularization in machine learning,
  
• Training base versus Test base, cross validation. 
• Gradient descent. Stochastic gradient descent.
  
• Expectation, Poisson Process, Bernoulli Process.

Learning Outcomes

• Apply learning in deep networks to real data
• Assess / Evaluate performance of learning algorithms
• Elaborate relations between different mathematical concepts of learning
• Judge limitations of algorithms
• Propose algorithms and models for learning in deep networks
• Apply Reinforcement Learning

Transversal skills

• Continue to work through difficulties or initial failure to find optimal solutions.
• Access and evaluate appropriate sources of information.
• Write a scientific or technical report.
• Manage priorities.

Teaching methods

ex cathedra lectures and  miniproject. Every week the ex cathedra lectures are interrupted for at least one in-class exercise which is then discussed in classroom before the lecture continues.  Additional exercises are given as homework or can be disussed in the second exercise hour.

Expected student activities

work on miniproject

solve all exercises

attend all lectures and take notes during lecture, participate in quizzes.

If you cannot attend a lecture, then you must read the recommended book chapters

Assessment methods

written exam (70 percent) and miniproject (30 percent)

Supervision

Resources

Bibliography

•  Textbook: Deep Learning by Goodfellow, Bengio, Courville (MIT Press)
•  Textbook: Reinforcement Learning by Sutton and Barto (MIT Press)

Pdfs of the preprint version for both books are availble online

Ressources en bibliothèque

• Reinforcement Learning by Sutton and Barto
• Deep Learning by Goodfellow, Bengio, Courville

Websites

• http://for videos and lecture slides https://lcnwww.epfl.ch/gerstner/VideoLecturesANN-Gerstner.html
• http://main web page is moodle

Videos

• http://yes, for most session.