Target

Duration

20 hours

Instructors

Nicoletta Noceti
UniGe | MaLGa & DIBRIS nicoletta.noceti@unige.it
Francesca Odone
UniGe | MaLGa & DIBRIS francesca.odone@unige.it

When

Jul 12 2022 , Jul 20 2022

Where

UniGe | DIBRIS, Via Dodecaneso 35, 16146 Genova, Room 506

Important Dates

Application deadline [EXTENDED]: May 31st
Notifications of acceptance: by June 16th
The school will be held in person

Abstract

Deep Learning (DL) is a branch of Machine Learning that has recently achieved astonishing results in a number of different domains. This course will provide a hands-on introduction to DL, starting from its foundations and discussing the various types of deep architectures and tools currently available. The theoretical classes will be coupled with hands-on activities in lab (in Python using Keras), which will constitute an integral part of the course, giving the possibility of practicing deep learning with examples from real-world applications, with particular focus on visual data. Besides well established approaches, the course will also highlight current trends, open problems and potential future lines of research.

Although the DL course can be taken independently, this year it will be held in synergy with the “Computer Vision Crash Course” (CVCC). Computer Vision is indeed one of the most classical and effective applications of DL in the real world. Contributions from the CVCC course will constitute a complementary deepening on basic principles of computer vision and visual perception in artificial agents, but also providing a guided tour through the use of deep learning for computer vision problems.

The program is integrated with that of CVCC and the contents of the two courses are complementary. Although this is not mandatory, students are encouraged to take both courses.

Tue 12/07 9.00-09.30 Welcome
Tue 12/07 09.30-13.00 Class Introduction to DL
Tue 12/07 14.30-16.00 Lab I NNs on images
Thu 14/07 9.30-11.00 Class Convolutional Neural Networks
Thu 14/07 14.30-16.00 Lab II CNNs
Mon 18/079.30-11.00 Class Autoencoders and GANs
Mon 18/0711:30-13.00 Lab III GANs
Tue 19/07 9.30-11.00 Class Dealing with sequences: from Recurrent Neural Networks to Transformers
Tue 19/07 11.30-13.00 Lab IV Transformers
Wed 20/07 9:30-13:00 Group project Optional activity for students willing to give an exam
Wed 20/07 14:30-16:00 Group project Optional activity for students willing to give an exam

Once accepted, each candidate has to follow the instructions in the acceptance email and proceed with the payment. The registration fee is non-refundable.

Fees
AIDA students: EUR 30
Non-UniGe students and postdocs: EUR 50
professors: EUR 100
professionals, in person: EUR 400
UniGe students and postdocs: free

To apply, complete the application form

Giulia Casu
UniGe | MaLGa & DIBRIS giulia.casu@ext.unige.it

Goodfellow, Y. Bengio and A. Courville, Deep Learning book, MIT Press, 2016.
Francois Chollet. Deep Learning with Python, Manning Pub., 2017
Slides, notebooks, and a list of bibliographical references and additional material will be provided to attendants. All the course material is in English.