School in AI: Deep Learning, Vision and Language for Industry - second edition

After the first extremely successful edition in February, we are happy to announce the second edition of the “School in AI: Deep Learning, Vision and Language for Industry”,  a new and intensive two-week training course at UNIMORE. It consists of a first week of “foundational” and a second week of “strengthening” AI training, followed by a practical experience, developing a project with the support of the course tutors and possibly in collaboration with companies.

The course is free for 30 graduated students and practitioners and entirely funded by the Emilia Romagna Region through the “Advanced Schools in Artificial Intelligence in Emilia-Romagna” project.

AI School is in partnership with AIACADEMY, AIMAGELAB, Artificial Intelligence Research and Innovation Center and hosted at Dipartimento di Ingegneria Enzo Ferrari

our program

First week

5 - 9 September 2022

Module 1: Fundamentals of Deep Learning – 45 hours

  1. Introduction to machine learning (with PyTorch)
  2. Basic linear classifiers
  3. Artificial neural networks
  4. Recurrent neural networks
  5. Autoencoders and self supervised learning

Module 2: Fundamentals of Computer Vision – 45 hours

  • Foundations of computer vision
  • Basic image processing: operations and descriptors
  • Convolutional neural networks
  • Motion analysis
  • Advanced deep architectures for visual cognitive systems

first week

Schedule Lessons from 5 to 9 September 2022
Aula P2.1 (Building MO25, second floor, first room) Dipartimento di Ingegneria "Enzo Ferrari"

monday 05
tuesday 06
Wednesday 07
Thursday 08
friday 09
9-11
Introduction to machine learning (Calderara)
Linear classifiers (Calderara)
Artificial neural networks (Calderara)
Recurrent neural networks (Calderara)
Autoencoders and self supervised learning (Porrello)
11-13
Introduction to Computer Vision (Cucchiara)
Image processing and descriptors (Grana)
Convolutional neural networks (Cucchiara)
Advanced deep architectures for visual cognitive systems (Baraldi)
3D Computer Vision (Vezzani)
14-16
Lab. of Introduction to Machine Learning (with PyTorch) (Boschini/Bonicelli)
Lab. of Basic Linear classifiers (Boschini/Bonicelli)
Lab. of Artificial neural networks (Porrello/Bonicelli)
Lab. of Recurrent neural networks (Boschini/Bonicelli)
Lab. of Autoencoders and self supervised learning (Porrello/Bonicelli)
16-18
lab. of Introduction to Computer Vision (Amoroso)
Lab. of Image processing and descriptors (Bolelli)
Lab. of Convolutional neural networks (Amoroso)
Lab. of Advanced deep architectures for visual cognitive systems (Amoroso)
Lab of 3D Computer Vision (Simoni)

first week

Schedule

MONDAY 14/02
9 - 11 Introduction to machine learning (Calderara)
h 9-10

School Inauguration
h 10-12
11 - 13 Introduction Computer Vision (Cucchiara)
h 12-13
14 - 16 Lab. of Introduction to machine learning (with PyTorch) (Boschini/Bonicelli)
16 - 18 Lab. of Foundations of computer vision (Amoroso)
TUESDAY 15/02
9 - 11 Linear classifiers (Calderara)
11 - 13 Image processing and descriptors (Grana)
14 - 16 Lab. of Basic linear classifiers (Porrello/Boschini)
16 - 18 Lab. of Image processing and descriptors (Bolelli)
WEDNESDAY 16/02
9 - 11 Artificial neural networks (Calderara)
11 - 13 3D Computer Vision (Vezzani)
14 - 16 Lab. of Artificial neural networks (Porrello/Bonicelli
16 - 18 Lab. of 3D Computer Vision (Simoni)
THURSDAY 17/02
9 - 11 Convolutional neural networks (Cucchiara)
11 - 13 Recurrent neural networks (Calderara)
14 - 16 Lab. of Recurrent neural networks (Boschini/Bonicelli)
16 - 18 Lab. of Convolutional neural networks (Amoroso)
FRIDAY 18/02
9 - 11 Autoencoders and self supervised learning (Porrello)
11 - 13 Advanced deep architectures for visual cognitive systems (Baraldi)
14 - 16 Lab. of Autoencoders and self supervised learning (Porrello/Bonicelli)
16 - 18 Lab. of Advanced deep architectures for visual cognitive systems (Baraldi)

our program

Second week

12 - 16 September 2022

Advanced Topics

  1. Anomaly detection and process monitoring in industry
  2. Automotive applications of artificial intelligence
  3. Continual Learning
  4. European Union Artificial Intelligence Act
  5. Explainability in artificial intelligence
  6. Geometric deep learning
  7. High performance computing and large-scale models
  8. Medical imaging
  9. Robot and 3D vision
  10. Vision and language (attention and Transformer Neural
    Network)

second week

Schedule Lessons from 12 to 16 September 2022
Aula P2.1 (Building MO25, second floor, first room) Dipartimento di Ingegneria "Enzo Ferrari"

monday 12
tuesday 13
Wednesday 14
Thursday 15
friday 16
9-11
Medical Imaging (Grana)
High performance computing and large-scale models (Fiameni)
European Union Artificial Intelligence Act (Cucchiara)
Vision and Natural language processing (Baraldi)
Robot and 3D vision (Vezzani)
11-13
Artificial Intelligence for bioinformatics (Ficarra)
Company meetings (Grana)
Geometric Deep learning (Rodolà)
Deep Learning and generative models (Spampinato)
Classification models (Mettes)
14-16
Deep Learning for Financial Forecasting (Calderara)
Company meetings (Grana)
Deep Learning for Fault Prediction (Paredes)
Explainability in Artificial Intelligence (Diaz Rodriguez)
Assisted project (Bolelli)
16-18
Assisted project (Bolelli)
Automotive applications of artificial intelligence (Baraldi)
Assisted project (Bolelli)
Assisted project (Bonicelli)
Assisted project (Bonicelli)

second week

Schedule

MONDAY 21/02
9 - 11 Medical Imaging (Grana)
11 - 13 Geometric deep learning (Rodolà)
14 - 16 Deep Learning for Financial Forecasting (Calderara)
16 - 18 Robot and 3D vision (Vezzani)
TUESDAY 22/02
9 - 11 Explainability in artificial intelligence (Natalia Diaz Rodriguez)
11 - 13 Continual Learning (Lomonaco)
14 - 16 Artificial Intelligence for Bioinformatics (Ficarra)
16 - 18 Assisted project (Bolelli)
WEDNESDAY 23/02
9 - 11 European Union Artificial Intelligence Act (Cucchiara)
11 - 13 Vision and language (attention and Transformer Neural Network) (Baraldi)
14 - 16 Assisted project (Bonicelli)
16 - 18 Assisted project (Bonicelli)
THURSDAY 24/02
9 - 11 High performance computing and large-scale models (Fiameni)
11 - 13 High performance computing and large-scale models (Fiameni)
14 - 16 Automotive applications of artificial intelligence (Baraldi)
16 - 18 Explainability in artificial intelligence
FRIDAY 25/02
9 - 11 Company meetings (Grana)
11 - 13 Company meetings (Grana)
14 - 16 Company meetings (Grana)
16 - 18 Company meetings (Grana)

LECTURERS

Rita Cucchiara holds a Degree in Electronic Engineering (1989) and a PhD in Computer Engineering (1993), both received at the University of Bologna. has been, since 2005, Full Professor of Information Processing Systems at the University of Modena and Reggio Emilia, where she is responsible for the AimageLab Laboratory and the AI Academy; she deals mainly with Artificial Vision and Deep Learning, with more than 350 publications on the subject. She is also Director of the interdepartmental Artificial Intelligence Research and Innovation Center AIRI, member of the Board of IIT (Italian Institute of Technology) and has been from 2018 to 2021 Director of CINI (National Interuniversity Consortium for Informatics) National Laboratory AIIS – Artificial Intelligence for Intelligent Systems.

Simone Calderara holds a Master’s degree in Computer Engineering (2005) and a PhD in Computer Engineering (2009), both received at the University of Modena and Reggio Emilia, where he is currently Associate Professor within the AimageLab group. His current research interests include machine vision and machine learning applied to human behaviour analysis, and visual monitoring in crowded environments. During his research career he has collaborated with national and international public and private institutions such as: Hebrew University of Jerusalem Interdisciplinary Center for Neural Computation, Center for Research in Computer University of Central Florida, and others. He has published more than 90 articles in international journals or conferences, he is also co-author of 3 chapters of books.

 

Costantino Grana graduated from the University of Modena and Reggio Emilia in 2000 and received his PhD in Computer Science and Engineering in 2004. He is currently Full Professor at the Department of Engineering Enzo Ferrari’ of the University of Modena and Reggio Emilia. His research interests mainly concern artificial vision and multimedia data processing: medical imaging, image processing, digital image analysis of historical manuscripts and other cultural heritage resources, Media images and recovery of videos and color-based applications. Costantino Grana has published 5 chapters of books, 38 articles in peer-reviewed international journals and more than 100 articles on international conferences.

Roberto Vezzani graduated in Computer Engineering in 2002 and received his PhD in Information Engineering in 2007 at the University of Modena and Reggio Emilia. Since 2016 he has been Associate Professor at the Department of Engineering ‘Enzo Ferrari’, he is part of the AimageLab group and has been director of the AIRI research center until 2021. His research interests mainly concern video surveillance systems, with particular attention to motion detection, detection and identification of people. He is author of about 80 articles published in international journals and conference proceedings. He is member of ACM, IEEE and CVPL.

Elisa Ficarra got a PhD in Systems and Computer Science at the Politecnico di Torino, Italy, in 2006. She was an Assistant and then Associate Professor in the same department until 2021. Since 2021 she has been a Full Professor at the Department of Engineering “Enzo Ferrari” at the University of Modena and Reggio Emilia, Italy.  She acts as scientific coordinator for the University of Modena and Reggio Emilia of funded European and Italian projects on Bioinformatics and Biomedical Image analysis, focusing on data mining and AI techniques for research on genetic pathologies. She also collaborates with several private foundations and companies on the same topics.  Her research led to more than 126 publications, including 52 journal papers.

Lorenzo Baraldi received his PhD (cum laude) in Information and Communication technologies from the University of Modena and Reggio Emilia, Italy, in 2018. He has been an intern researcher at Facebook AI Research (FAIR) in 2017. He is currently Assistant Professor at the Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia. He is author or co-author of over 40 publications in scientific journals and international conferences. His filed of research include image processing, video comprehension, deep learning, and multimedia.

Angelo Porrello obtained a Master’s Degree in Computer Engineering in 2017 from the University of Modena and Reggio Emilia.  He pursued a Ph.D. programme in Information and Communication Technology during the three-year period 2019-2021; at the moment, he works as Research Fellow within the AImageLab Group at the Department of Engineering “Enzo Ferrari”. His research interests focus on Deep Learning techniques: more precisely on the fields of Continual Learning, Re-Identification, and Anomaly Detection. He is the author or co-author of more than 10 publications in scientific journals and international conference proceedings.

Giuseppe Fiameni is a Data Scientist at NVIDIA where he oversees the NVIDIA AI Technology Centre in Italy, a collaboration among NVIDIA, CINI and CINECA to accelerate academic research in the field of AI. He has been working as HPC specialist at CINECA, the largest HPC facility in Italy, for more than 14 years providing support for large-scale data analytics workloads. Research interests include large scale deep learning models, system architectures, massive data engineering, video action detection.

Roberto Paredes is Full Professor of Computer Science at Universitat Politècnica de València in Spain (UPV). He has been the first Director of the Pattern Recognition and Human Language Technology Research Center and President of the AERFAI (Pattern Recognition and Image Analysis National Association). His research interests include deep learning, machine learning, pattern recognition, biometrics and their application to computer vision and big data analysis. He has participated in several National and European Research Projects and currently he is the Lead Developer of the European Distributed Deep Learning Library under the DeepHealth European Project. Professor Paredes is the coauthor of more than 130 articles in international journals and international conferences. He has received different awards like the Best Face Verification Algorithm in AVBPA 2003.

Natalia Díaz-Rodríguez is currently researcher and docent at the DaSCI Andalusian Research Institute in data science and computational intelligence at the Dept. of Computer Science and Artificial Intelligence. Earlier, she worked in Silicon Valley, CERN, Philips Research, University of California Santa Cruz and with FDL Programme with NASA. She was also Assistant Prof. of Artificial Intelligence at the Autonomous Systems and Robotics Lab (U2IS) at ENSTA, Institut Polytechnique Paris, INRIA Flowers team on developmental robotics. Her current research interests include deep learning, explainable Artificial Intelligence (XAI), Responsible AI and AI for social good. Her background is on knowledge engineering and is interested in neural-symbolic approaches to practical applications of AI.

Emanuele Rodolà is Full Professor of Computer Science at Sapienza University of Rome, where he leads the GLADIA group of Geometry, Learning and Applied AI, funded by an ERC Grant and a Google Research Award, and acts as the Director of the PhD in Computer Science. Previously, he was Assistant and then Associate Professor at Sapienza (2017-2020), a postdoc at USI Lugano (2016-2017), an Alexander von Humboldt Fellow at TU Munich (2013-2016), and a JSPS Research Fellow at The University of Tokyo (2013). He received a number of research prizes, has been serving in the program and organizing committees of the top rated conferences in computer vision, machine learning and graphics, founded and chaired several successful workshops. His research interests lie at the intersection of geometry processing, graph / geometric deep learning, applied AI and computer vision, and has published more than 100 papers in these areas.

Pascal Mettes is an assistant professor in computer vision at the University of Amsterdam. He received his PhD (2017) under prof. Cees Snoek at the University of Amsterdam. He was a visiting scientist at Columbia University (2016) under prof. Shih-Fu Chang and at the University of Tübingen (2021) under prof. Zeynep Akata. His research focuses on discovering and embedding prior knowledge in deep networks for visual understanding. He is organizer of the ICCV 2021 workshop of Structured Representations for Video Understanding, the Netherlands Conference on Computer vision 2022, and the ECCV 2022 tutorial on Hyperbolic Representation Learning for Computer Vision.

Concetto Spampinato holds a Degree in Electronic Engineering (1989) and a PhD in Computer Engineering (1993), both received at University of Catania, where is associate professor. In 2007 he was visiting researcher at the School of Informatics, University of Edinburgh (UK) and Since April 2018 he is “Courtesy” Assistant Professor at the Center for Research in Computer Vision, University of Central Florida (USA). He also funded and currently leads the Pattern Recognition and Computer Vision Lab at the University of Catania.  His research interests lie in learning-based computer vision and pattern recognition, with a particular focus on human-based and brain-driven computation systems as well as on generative adversarial models. He has co-authored over than 150 publications in international refereed journals and conference proceedings.

 

info

Course Details

Participation fee: None. The course is completely free.

Credits granted: The Postgraduate Course provides the certification of 15 ECTS (expendable in Master’s Degree Courses that recognize them). In order to get the credits, 75% of the lessons must be attended and after the lesson period an independent project must be delivered with a positive evaluation, by the deadline of 30 November 2022.

Location: Dipartimento di Ingegneria “Enzo Ferrari”, Via P. Vivarelli 10, 41125 Modena.

Duration of face-to-face lessons: Two weeks, from 5 to 16 September 2022.

Application deadline: 30 June 2022 at 13:00.

Selection: Based on qualifications only (bachelor’s or master’s degree grade and curriculum vitae).

Availabilities: The course includes 30 free places, including free accomodation (if requested), assigned on the basis of the degree grade and the CV evaluation.

AI ACADEMY

Creating innovative solutions of Artificial Intelligence is a complex task, requiring specialized expertise to understand which solutions are ideal for your company. The demand for professionals with those skills is soaring, and the acquisition of these skills is the goal of the School in AI: Deep Learning, Vision and Language for Industry.

The course is organized in partnership with the AI ACADEMY UNIMORE that connects the major technological players with sites in Emilia Romagna and fosters life-long learning initiatives on the AI fields and related subfields.

 

Companies affiliated with AI ACADEMY:

enroll

Apply

Official information on the UNIMORE page: Link

Read the call carefully!

Applications deadline: 30 June 2022 at 13:00

Progetto triennale di alta formazione in ambito culturale, economico e tecnologico ai sensi dell’art. 2 della legge regionale n. 25/2018 approvato con deliberazione di Giunta regionale n.1251/2019.