Ritratto di fabio.galasso@uniroma1.it

AML and FDS lectures will start in September, 2022.

The dates, times and places will be communicated in due course on the course websites (see links below).

Classes are in presence and from remote. Remote connection credentials have been distributed via the mailing lists (see details on how to join them on the course websites). Please join the mailing lists with your institutional email addresses. If you are a first-year master's student and did not receive your institutional address yet due to specific situations, please request access to the group but also send an email detailing i. the circumstance; ii. a proof of your acceptance; and iii. a proof of your identity. Requests from non-institutional addresses without those cannot be accepted.

 

Advanced Machine Learning (AML):

https://sites.google.com/di.uniroma1.it/aml-2022-2023

The (blended) online lectures are on zoom (credentials are communicated via the Google group (https://groups.google.com/a/di.uniroma1.it/g/aml-22-23)

 

Fundamentals/Foundations of Data Science and Laboratory (FDS):

https://sites.google.com/di.uniroma1.it/fds-2022-2023

The (blended) online lectures are on zoom (credentials are communicated via the Google group (https://groups.google.com/a/di.uniroma1.it/g/fds-22-23).

Insegnamento Codice Anno Corso - Frequentare Bacheca
ADVANCED MACHINE LEARNING 10589621 2021/2022

The course will present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It will include theory and practical coding, as well as a final hands-on project.

In the first part of the course, I will introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I will 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 will further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part will include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).

 

In the second part of the course, I will 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 will 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 will 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.

 

For more information see the course website: https://sites.google.com/di.uniroma1.it/aml-2022-2023

FUNDAMENTALS OF DATA SCIENCE AND LABORATORY 1047264 2021/2022

The course is an introduction to the basics of Data Science as well as the relating topics from Data Mining, Machine Learning and Image Analysis, using the Python programming language.

 

I will cover the fundamental models, algorithms and approaches to deal with data from a Data Science and Machine Learning perspective, including the data preparation, the feature engineering, the model design and its optimization and evaluation. Topics from the course will include: basics of digital image processing, regression, classification with discriminative and generative models, optimization, bias/variance, regularization, clustering, dimensionality reduction, and a brief introduction to neural networks.

In the laboratory classes (for data science students only) I will introduce: the basics of Python, Numpy, data structures and Pandas, plotting, Scikit-learn, and sample programming of machine learning models from the course.

 

For more information see the course website: https://sites.google.com/di.uniroma1.it/fds-2022-2023

ADVANCED MACHINE LEARNING 10589621 2021/2022

The course will present advanced concepts of machine learning and their application in computer vision via deep neural network (DNN) models. It will include theory and practical coding, as well as a final hands-on project.

In the first part of the course, I will introduce state-of-the-art DNN models for classification, showing how to estimate which objects are within an image. I will 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 will further discuss DNNs for multi-task objectives (joint detection, pose estimation, re-identification, segmentation, depth estimation etc). This first part will include DNNs which apply to video sequences, by leveraging memory (e.g. LSTMs) or attention (Transformers).

 

In the second part of the course, I will 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 will 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 will 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.

 

For more information see the course website: https://sites.google.com/di.uniroma1.it/aml-2022-2023

FOUNDATIONS OF DATA SCIENCE 1047627 2021/2022

The course is an introduction to the basics of Data Science as well as the relating topics from Data Mining, Machine Learning and Image Analysis, using the Python programming language.

 

I will cover the fundamental models, algorithms and approaches to deal with data from a Data Science and Machine Learning perspective, including the data preparation, the feature engineering, the model design and its optimization and evaluation. Topics from the course will include: basics of digital image processing, regression, classification with discriminative and generative models, optimization, bias/variance, regularization, clustering, dimensionality reduction, and a brief introduction to neural networks.

In the laboratory classes (for data science students only) I will introduce: the basics of Python, Numpy, data structures and Pandas, plotting, Scikit-learn, and sample programming of machine learning models from the course.

 

For more information see the course website: https://sites.google.com/di.uniroma1.it/fds-2022-2023

ADVANCED MACHINE LEARNING 10589621 2020/2021
FUNDAMENTALS OF DATA SCIENCE AND LABORATORY 1047264 2020/2021
FOUNDATIONS OF DATA SCIENCE 1047627 2020/2021
FUNDAMENTALS OF DATA SCIENCE AND LABORATORY 1047264 2019/2020
FOUNDATIONS OF DATA SCIENCE 1047627 2019/2020
ADVANCED MACHINE LEARNING 10589621 2019/2020
FOUNDATIONS OF DATA SCIENCE 1047627 2018/2019
FOUNDATIONS OF DATA SCIENCE 1047627 2017/2018
FOUNDATIONS OF DATA SCIENCE 1047627 2016/2017

On Thursdays at 13:30-15:30 upon request, either remote (link will be provided) or in presence (Room 105, building E, via Regina Elena 295)

Prof. Fabio Galasso heads the Perception and Intelligence Lab (PINLab) at the Dept. of Computer Science, Sapienza University in Rome (Italy). Our group is interested in fundamental research and innovation transfer in computer vision and machine learning. Our specific research interests include distributed and multi-agent intelligent systems, perception (detection, recognition, re-identification, forecasting) and general intelligence (reasoning, meta-learning, domain adaptation), within sustainable (low-power-consumption and constrained-computational-resource sensors and devices) and interpretable (interpretable and verifiable AI) frameworks.

Previously, Fabio founded and directed the Computer Vision Department at OSRAM (Munich, Germany), an international team conducting R&D in artificial intelligence, computer vision and machine learning, in relation to smart lighting applications.
We made long-term strategic propositions and cared about the entire life cycle of ideas, from the creation of new value propositions to the implementation of prototypes and pilots. Pilot installations include large industrial partners such as Edeka. Innovation transfer successes include the VISN product, which was awarded the 2019 IoT/WT Innovation World Cup, the 2019 Digital Champions Award, and the 2018 Deutscher Digital Award.

Prior to OSRAM, he has conducted research on video analysis and segmentation, scene understanding and clustering at the University of Cambridge (UK) and at the Max Planck Institute for Informatics (Germany).
He received his Master's Degree cum laude from the RomaTre University (Italy) and his PhD from the University of Cambridge (UK), following research work on texture analysis and 3D reconstruction.
Before and after his Master's Degree, he gained experience as a Researcher in the Ericsson Laboratories and as a Project Engineer in Telecom Italia. In his career, he has been involved in consulting work relating to computer vision.

Fabio has recently coordinated a Marie Sk odowska-Curie Actions project (Horizon 2020) and was Principal-Co-Investigator in several German-funded projects, from the Ministry of Education and from the Ministry of Economics. He has served as area and industrial chair at international conferences, as reviewer for journals and conferences, and as co-chair of international workshops.

More information is available at: https://fgalasso.bitbucket.io/