Welcome! This is the home page of the "Advanced Machine Learning" course, taking place in the winter semester of 2020/2021.
The course is part of the Master's Degree in Data Science -- Sapienza University of Rome -- organized jointly by the departments of Computer Science (DI), Information and Automation Engineering (DIAG) and Information, Electronics and Telecommunication Engineering (DIET), and Statistics (DSS).
You like the subject? why not consider a Ph.D. ? See adverts on my web-page or simply ask me!
Important: subscribe to the course mailing list to receive slides, course material, assignments and news. Click on this link.
Note: join the mailing list with your institutional email.
The course takes place @:
Room B2 (Via Ariosto, 25 -- Ground Floor Side B) on Tuesdays 9:00-12:00 (note: updated time from Nov 17th)
Room 13 (Tumminelli building -- CU007 map) on Fridays 16:00-19:00
The course starts on October 6th, 2020.
Update (Nov 6th): lectures are remote-only starting from this date.
Please also refer the Data Science website for the class schedule.
Prof. Fabio Galasso, web-page, email: galasso remove_this @di DOT uniroma1 DOT it
The course would present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It would include theory and practical coding, as well as a final hands-on project.
In a first part of the course, I would introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I would then showcase regression, as applied to detection (where the objects are in the image), pose estimation (whether people stand, sit or crunch) and re-identification (estimating a unique vector representation for each person). I would further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part would include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).
In a second part of the course, I would discuss generalization and the effective use of labelled and unlabelled data for learning. Further to transfer learning (how pre-trained models may be deployed for other tasks), I would discuss multi-modal (with different sensor modalities such as depth or thermal cameras) and self-supervision (e.g. training the DNN model by solving jigsaw puzzles) to auto-annotate large amounts of data. Finally, I would present domain adaptation (e.g. apply daytime-detectors for night vision) and meta-learning, a most recent framework to learn how to learn a task, e.g. online or from little available data.