91250 - Deep Learning

Academic Year 2022/2023

Learning outcomes

At the end of the course, the student understands the foundational ideas, recent advances and application potential of deep neural systems. The student understands supervised and unsupervised techniques, basic neural topologies, methods for visualizing and understanding the behavior on neural nets, adversarial and generative techniques, reinforcement learning, and recurrent networks. The student is able to apply such technologies to solving classification problems in realistic domains.

Course contents

machine learning
analisi
algebra
pyhtonThe course starts with an introduction to Deep Learning, Neural Networks and their typical learning mechanism: the backpropagation algorithm.

We shall discuss the main types of neural nets: feed forward,
convolutional and recurrent, providing concrete examples and discussing successful neural architectures for image processing, localization, segmentation, style transfer, text processing and many other tasks.

We shall investigate techniques to visualize the behavior of hidden units (tightly related to deep dreams and inceptionism), techniques to fool neural networks, and modern generative approaches comprising Variational Autoencoders, Generative Adversarial Networks, and their most recent developments.

The final part of the course will be devoted to an introduction to Deep Reinforcement Learning, with applications to the design of intelligent agents for video games, autonomous driving and other situations requiring complex and adaptive behaviors.

Prerequsites

Knowledge of the following topics is required:

  • machine learning
  • analysis
  • algebra
  • pyhton

 

Readings/Bibliography

Suggested readings:

 

Specific pointers to on line material will be provided at each lesson, in addition to the slides of the course.

Teaching methods

Frontal lessons based on slides, with discussion of practical examples via pyhton notebooks.

We also foresee  laboratories held by tutors, for 12 additional hours, 

Teaching methods may be subject to variation due to the Corona Virus emergency.

Assessment methods

Individual project on topics defined by the teacher.

 The grade can be optionally integrated by an oral examination.

The assesment method may change in relation with the attendance.

Teaching tools

Lectures will make extensive usage of slides. Working examples will be delivered by means on python notebooks.

Office hours

See the website of Andrea Asperti