93319 - INTRODUZIONE ALL'APPRENDIMENTO AUTOMATICO

Learning outcomes

During the course, the student will be introduced to the complex themes pertaining to the simulation of intelligent behavior by means of machines, with practical experimentation of basic machine learning techniques for different tasks: supervised, unsupervised, with reinforcement. The course will also provide rudiments of image processing, since images will be extensively used as experimental test bench for the aforementioned learning techniques.

Course contents

The first part of the course provides a general introduction to the field of machine learning in its typical forms: supervised, unsupervised, and reinforcement learning. Traditional topics such as decision tree learning, logistic regression, Bayesian networks, and Support Vector Machines will be covered.

The second part of the course focuses on Neural Networks and their typical learning mechanism: the backpropagation algorithm. We will discuss the main types of neural networks: feedforward, convolutional, and recurrent, along with their practical applications. We will also investigate techniques to visualize the effects of hidden units (closely related to deep dreams and inceptionism), as well as several generative approaches, including Generative Adversarial Networks. Topics related to Object Detection and Semantic Segmentation will also be briefly discussed.

Readings/Bibliography

Teacher's slides.

During the course, additional links to relevant documents and sites will be provided.

Teaching methods

Frontal lessons integrated with practical exemplifications

We also foresee additional laboratories held by tutors for a total of 12 hours

Assessment methods

Individual project on a topic defined by the teacher, possibly integrated by a written quiz.

Teaching tools

The course will make use of several opens source libraries for Machine Learning. In particular we shall mostly use

• scikit-learn
• Tensorflow/Keras

Office hours

See the website of Andrea Asperti