The following short courses are offered to AIDA Students (PhD students, Post-doc researchers, possibly qualified MSc students of AIDA Members) and other students worldwide.

AIDA Members are university partners of ICT48 Projects: AI4Media, HumanE AI Network, TAILOR, VISION.

Student eligibility: PhD students, Post-doc researchers, MSc students of AIDA Members can participate on preferential favorable terms, according to the rules of each short course. Qualified MSc students from AIDA Members can participate on availability basis.

Registration: Interested students should enter the course webpage to register.

Spring Course Offers

Description: Introduction to Machine Learning, Artificial Neural Networks, Perceptron, Multilayer perceptron. Backpropagation, Deep neural networks. Convolutional NNs, Deep learning for object detection, Deep Semantic Image Segmentation, Generative Adversarial Networks, Recurrent Neural Networks. LSTMs, Data Clustering, Decision Surfaces. Support Vector Machines, Distance-based Classification, Dimensionality Reduction, Kernel Methods, Bayesian Learning, Deep Reinforcement Learning, CVML Software Development Tools.

Institution: Aristotle University of Thessaloniki

Department: School of Informatics

Short Course

ECTS: 1.5

Level: MSc/Senior undergraduate

Semester: Spring Semester

Start Day, Duration: 27th April 2021, 2 Days

Language: English

Participation mode: teleconference/tele-exams

Participation terms: See course website

Lecturer: Prof. Ioannis Pitas pitas@csd.auth.gr

Link to course: https://icarus.csd.auth.gr/spring-cvml-short-course-machine-learning-and-deep-neural-networks/

Description: This is an introductory course to the theory and applications of Graph Neural Networks (GNN) and to related topics in Neural-Symbolic Computation. The course gives the foundations on neural computation involving patterns represented by graphs in fields ranging from computer vision to bioinformatics. In addition, GNN will be presented for different applications in the case of graph-based domains, where inferential processes are expected to involve also the neighbors of vertexes (e.g. social networks). Finally, the diffusion mechanisms taking place by GNN will be integrated with more general Neural-Symbolic models where the decision mechanisms need to be coherent with external representations of environmental knowledge.

  1. 9:00 - 12:00, February 4 2021 - Neural computation on directed graphs, Diffusion
    on graphs, GNN
  2. 9:00 - 12:00, February 11 2021 - Convolution on graphs, lab experiments
  3. 9:00 - 12:00, February 18 2021 - Neuro-symbolic computation
  4. 9:00 - 11:00, February 25 2021 - Lab experiments
  5. 11:00 - 12:00, February 25 2021 - Seminar by Petar Veličković, Deep Mind

Institution: Université Côte d'Azur, France

Department:

Short Course

ECTS: N/A

Level: Master 2

Semester: Spring

Start Day, Duration: Starts on Feb. 4 2021, ends on Mar. 4 2021, 5 weeks, Thursdays 9:00 - 12:00, CET

Language: English

Participation mode: Zoom

Participation terms: 

Lecturer: Prof. Marco Gori, MAASAI, Université Côté d’Azur and SAILab, University of Siena
Course assistance and seminars:

  • Dr. Petar Veličković, Deep Mind
  • Dr. Michelangelo Diligenti, Google and SAILab, University of Siena
  • Dr. Giuseppe Marra, KU Leuven
  • Matteo Tiezzi, SAILab, University of Siena

For registration, please contact Lucile Sassatelli lucile.sassatelli@univ-cotedazur.fr

Link to course: http://web.univ-cotedazur.fr/en/idex/formations-idex/data-science/

Description: Data pre-procesing and multimedia content representation. Data clustering, Data classification

Institution: University "Politehnica" of Bucharest, Romania

Department:

Short Course

ECTS:

Level: 

Semester: Spring

Start Day, Duration: March 8th 2021

Language: English

Participation mode: Zoom

Participation terms: 

Lecturer: Prof. Bogdan Ionescu

Link to course: 

Description: The University of Applied Sciences of Western Switzerland and University of Bordeaux are happy to present this lecture series as a preview of a longer course that may start in Autumn 2021. This course will cover topics such as the definition of AI interpretability, saliency and attention models and the explainability of deep models by feature attribution methods and concept-based attribution with Concept Activation Vectors and Regression Concept Vectors.

Institution: HES-SO Valais Switzerland, University of Geneva, University of Bordeaux

Department: Computer Science

Short Course

ECTS: 1.5

Level: M.Sc., Ph.D.

Semester: Spring Semester

Start Day, Duration: on May 20,  duration 5 courses scheduled as in the following

  • May 20 16.00 – 17.30 (CEST):  Course opening and Lect. 1 (Prof. Henning Müller and Mara Graziani): The where and why of interpretability
  • May 27th 16.00 -18.00: Course Lecture 2 (by Prof. Jenny Benois-Pineau): From attention models and saliency to the explainability of deep networks
  • June 7 16.00-17.00: Course Lecture 3 (Mara Graziani): The three dimensions of interpretability, Activation Maximization and Feature Attribution
  • June 10 16.00-17.00: Course Lecture 4 (Mara Graziani) : Concept-based interpretability
  • June 14  16.00-17.30 : Course Lecture 5 (Mara Graziani) : How to evaluate your results + open Q&A

Language: English

Participation mode: Online Videos and Teams Meetings

Participation terms: 

Lecturer: Prof. Henning Müller henning.mueller@hevs.ch, M.Phil. Mara Graziani mara.graziani@hevs.ch and Prof. Jenny Benois-Pineau jenny.benois-pineau@u-bordeaux.fr

Link to course: https://introinterpretableai.wordpress.com/

Description: 

Institution: Université Cote d'Azur

Department:

VShort Courses 

ECTS: 2

Level: PhD (for beginners. Each module 40’’ to 50’’.)

Semester: Spring Semester

Start Day, Duration: 12-16 July 2021

Language: English

Participation mode: 

Participation terms: 

Lecturer: E. Ricci, M. Gori, A. Barto, H. Ney, D. Jimenez Rezende

Link to course: