91934 - Applied Machine Learning - Advanced

Learning outcomes

The course aims to apply Machine Learning to complex real-world datasets and relies on the basic concepts introduced in the course "Applied Machine Learning", that is propedeutic. At the end of the course the student has competences on how to exploit different hardwares for Machine Learning and Deep Learning solutions, both on-premise and via cloud. The student will be also introduced to most recent approaches and active areas of work in the Artificial Intelligence community worldwide.

Course contents

- Applying Machine Learning models to real world datasets

- Improving Deep Learning models

- Modern ML frameworks (from ensorflow to Pytorch)

- Technology behind ML/DL at scale

- Tips and tricks to be effective in building and training models

Readings/Bibliography

Material (textbooks and online available) will be suggested at the lectures.

Teaching methods

A mixture of traditional lectures with slides, and innovative collaborative hands-on based on Jupyter notebooks, Google colab, and credits for access to cloud resources.

Assessment methods

A project (code) to be discussed a-priori with the teacher.

Teaching tools

Slides, online material.

Office hours

See the website of Daniele Bonacorsi