Deep Learning School @UCA 2021

 

UCA Event 2021, from July 12-16

The Deep Learning School @UCA is back! This program will be in English, online and safe, open to more attendees. Participants will be able to attend online and at their own local time. This event is certified by the Interdisciplinary Institute of Artificial Intelligence (3IA Côte d'Azur).
Whether you are a researcher, an engineer, an expert in "Deep Learning" or eager to learn more about these crucial methods at the core of modern AI, this program is for you. It includes:

  • 5 Lectures given by High-profile Speakers, internationally renowned in the field; these lectures will take place in the morning or in the afternoon.
  • 5 "Expert Labs" on to the topics of the lectures, and supervised by subject-matter experts; these labs will take place the same day of the corresponding lecture, in the afternoon or in the morning accordingly.
 

Speakers

                             Hermann Ney

             Elisa Ricci

             

                      Danilo J. Rezende

            Marco Gori

July 12th

Lecture | from 9am to 12:15am | Speech Recognition and Machine Translation: From Bayes Decision Theory to Machine Learning and Deep Neural Networks by Prof. Hermann Ney

The last 40 years have seen a dramatic progress in machine learning and statistical methods for speech and language processing like speech recognition, handwriting recognition and machine translation. Many of the key statistical concepts had originally been developed for speech recognition. Examples of such key concepts are the Bayes decision rule for minimum error rate and sequence-to-sequence processing using approaches like the alignment mechanism based on hidden Markov models and the attention mechanism based on neural networks.
Recently the accuracy of speech recognition, handwriting recognition machine translation could be improved significantly by the use of artificial neural networks and specific architectures, such as deep feedforward multi-layer perceptrons and recurrent neural networks, attention and transformer architectures. We will discuss these approaches in detail and how they form part of the probabilistic approach.

Lab | from 2pm to 5:15pm | Speech Recognition and Machine Translation

This lab will be dedicated to audio data analysis and speech recognition. In this lab, we will experiment how deep learning works with audio signals; more specifically, we will learn how to build and train some efficient deep learning models to recognize speech by combining CNNs, RNNs, and Attention mechanisms.

July 13th

Lecture | from 2pm to 5:15pm |  Reinforcement Learning and Neural Networks by Prof. Andrew G. Barto 

The union of reinforcement learning (RL) and deep neural networks has recently produced remarkable contributions to AI. A better appreciation of these contributions can be gained by understanding that computational studies of RL and neural networks have tightly intertwined histories. Both originated as  hypotheses about how brains function and learn, and their development has been coupled from the very beginning. The computational power of deep RL united with recent results about the brain’s reward system point to how a next round of advances may arise. 

Lab | from 9am to 12:15am | Deep Reinforcement Learning 

While applications of RL are typically limited to discrete, low-dimensional constraints, recent advances in Deep RL (DQN for Atari 2600, AlphaGo, and more lately AlphaGo Zero) have demonstrated human-level or super-human performance in complex, high-dimensional spaces.
This lab will be dedicated to Deep Reinforcement learning. This lab is meant to provide a first experience on using Deep Reinforcement Learning (DRL), for both synthetic and more realistic problems.

July 14th

Lecture | from 9am to 12:15am | by Prof. Elisa Ricci

To be precised.

Lab | from 2pm to 5:15pm |  

To be precised.

July 15th

Lecture | from 9am to 12:15am | Deep Generative Models: Foundations, applications and open problems by Danilo J. Rezende

Generative models are at the forefront of machine learning research because of the promise they offer for allowing data-efficient learning, and for model-based reinforcement learning. This talk will cover a few standard methods for approximate inference and density estimation and recent advances which allow for efficient large-scale training of a wide variety of generative models. Finally, I'll demonstrate several important applications of these models to density estimation in fundamental sciences, missing data imputation, data compression and planning.

Lab | from 2pm to 5:15pm | Deep Generative Models

In this lab, we will implement several likelihood-based deep generative models. We will focus on variational autoencoders (VAEs) and variations thereof, and will also discuss normalizing flows and autoregressive models. Applications will include dimensionality reduction and missing data imputation.

July 16th

Lecture | from 9am to 12:15am | Graph Neural Networks and Neural-Symbolic Computation by Prof. Marco Gori

This lecture will focus on 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 discussion 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.

Lab | from 2pm to 5:15pm | Graph Neural Networks and Neural-Symbolic Computation

The lab will start with a brief introduction to the available GNN frameworks, then how to represent a graph, and how to define a GNN Model in the available frameworks. We will then explore learning tasks such as Node Classification, Graph Classification, or Link Prediction. We will finish with one or two projects among Graph Visualization, Subgraph matching, Clique detection and communities, Learning PageRank.

 

Speakers
 

Hermann Ney

Hermann Ney is a professor of computer science at RWTH Aachen University, Germany.

His main research interests lie in the area of statistical classification, machine learning and neural networks with specific applications to speech recognition, handwriting recognition, machine translation and other tasks in natural language processing.

He and his team participated in a large number of large-scale joint projects like the German project VERBMOBIL, the European projects TC-STAR, QUAERO, TRANSLECTURES, EU-BRIDGE and US-American projects GALE, BOLT, BABEL. His work has resulted in more than 700 conference and journal papers with an h index of 100+ and 60000+ citations (based on Google scholar). More than 50 of his former PhD students work for IT companies on speech and language technoloy.

The results of his research contributed to various operational research prototypes and commercial systems. In 1993 Philips Dictation Systems Vienna introduced a product for large-vocabulary continuous-speech recognition. In 1997 Philips Dialogue Systems Aachen introduced a spoken

dialogue system for traintable information via the telephone. In VERBMOBIL, his team introduced the phrase-based approach to data-driven machine translation, which in 2008 was used by his former PhD students at Google as starting point for the service Google Translate. In TC-STAR, his team built the first research prototype system for spoken language translation of real-life domains.

Awards: 
2005 Technical Achievement Award of the IEEE Signal Processing Society;
2013 Award of Honour of the International Association for Machine Translation;
2019 IEEE James L. Flanagan Speech and Audio Processing Award;
2021 ISCA Medal for Scientific Achievements.

Andrew G. Barto

Andrew Barto is Professor Emeritus of Computer Science, University of Massachusetts Amherst, having retired in 2012. He served as Chair of the UMass Department of Computer Science from 2007 to 2011. He received a B.S. with distinction in mathematics from the University of Michigan in 1970, and a Ph.D. in Computer Science in 1975, also from the University of Michigan. He joined the Computer Science Department of the University of Massachusetts Amherst in 1977 as a Postdoctoral Research Associate, became an Associate Professor in 1982, and a Full Professor in 1991.

Before retiring he co-directed the Autonomous Learning Laboratory at UMass Amherst, which produced many notable machine learning researchers. He is currently an Associate Member of the Neuroscience and Behavior Program of the University of Massachusetts. He serves as an associate editor of Neural Computation, as a member of the Advisory Board of the Journal of Machine Learning Research, and as a member of the editorial board of Adaptive Behavior.

Professor Barto is a Fellow of the American Association for the Advancement of Science, a Fellow and Life Member of the IEEE. He received the 2004 IEEE Neural Network Society Pioneer Award for contributions to the field of reinforcement learning, the IJCAI-17 Award for Research Excellence for groundbreaking and impactful research in both the theory and application of reinforcement learning, and a University of Massachusetts Neurosciences Lifetime Achievement Award in 20019. He has published over one hundred papers or chapters in journals, books, and conference and workshop proceedings. He is co-author with Richard Sutton of the book "Reinforcement Learning: An Introduction," MIT Press, 1998, which has received over 25,000 citations. A much expanded second edition was published in 2018.

Elisa Ricci

Elisa Ricci is an Associate Professor with Department of Information Engineering and Computer Science (DISI) at the University of Trento and the head of the Deep Visual Learning research group at Fondazione Bruno Kessler (FBK). She is the scientific manager of the Joint Laboratory on Vision and Learning between FBK and DISI. Her research interests are directed to the development of deep learning algorithms and, in particular, of transfer learning and domain adaptation methods, with applications in the field of computer vision, multimedia analysis and robot perception.

Elisa received her MSc (2004) and PhD degree (2008) in Electrical Engineering from the University of Perugia. Previously, she was an Assistant Professor at the University of Perugia (2011-2017) and a researcher at the Idiap Research Institute (2009) and FBK (2010). She has been a visiting researcher at the Swiss Federal Institute of Technology and the University of Bristol. 

Elisa has co-authored more than 100 scientific publications and she regularly publishes in top-tier journals and conferences in computer vision and multimedia (CVPR/ICCV/NeurIPS/ACM MM, IEEE TPAMI, IJCV, IEEE TMM, IEEE TIP). Her publications have been cited over 5,500 times and her Google Scholar H-index is 39. She has received numerous awards for her scientific activity (Best paper award ACM MM 2015, INTEL Best Paper ICPR 2016, etc). She is a member of the editorial board of the journals IEEE Transactions on Multimedia, ACM Trans on Multimedia Computing Communications and Applications and Multimedia Systems Journal (MMSJ). She is the Program Chair of ACM MM 2020, the Diversity Chair of ACM MM 2022, Track Chair of ICPR 2020, Special Session Chair at ICME 2022. She was/is Area Chair at WACV 2021, AISTATS 2021, BMVC 2018-2020, ICMR 2019, Senior Program Committee member of IJCAI 2019, ACM Multimedia 2016-2019, Area Chair at ECCV 2016, ICCV 2017 and Associate Editor at ICRA 2018, 2019, 2021. 

She is/was the Principal Investigator and/or participated to several national and international projects. Elisa Ricci is also involved in several industrial projects and collaborations with companies, both at national and international level. Currently, she is the principal investigator of the project BONSAI – Analyzing Human Behaviors with Online and Structured Adaptation  funded by Huawei Technologies.

Danilo J. Rezende

Danilo Jimenez Rezende is a Senior Staff Research Scientist and Team Lead at Google DeepMind, where I work at the intersection of probability, statistics, machine learning and decision making.

He holds a joint BA in Physics and MSc in Theoretical Physics from Ecole Polytechnique (Palaiseau – France) and from the Institute of Theoretical Physics (SP – Brazil) and a Ph.D. in Computational Neuroscience at Ecole Polytechnique Federale de Lausanne, EPFL (Lausanne – Switzerland).

His research focuses on scalable inference methods, generative models of complex data (such as images, video, 3D perception, field theories from physics), applied probability and unsupervised learning. I am also very interested and invested in applying ML to fundamental physics problems (such as molecular dynamics and lattice-QCD).

Marco Gori

Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy, working partly at the School of Computer Science (McGill University, Montreal). In 1992, he became an Associate Professor of Computer Science at Università di Firenze and, in November 1995, he is currently leading  the Siena Artificial Intelligence Lab (SAILAB).  Professor Gori is primarily interests in machine learning with applications to pattern recognition, Web mining, game playing, and bioinformatics. He has recently published the monograph “Machine Learning: A constraint-based approach,” (MK, 560 pp., 2018), which contains a unified view of his approach. His pioneering role in neural networks has been emerging especially from the recent interest in Graph Neural Networks, that he contributed to introduce in the seminal paper “Graph Neural Networks,” IEEE-TNN, 2009.

Professor Gori has been the chair of the Italian Chapter of the IEEE Computation Intelligence Society and the President of the Italian Association for Artificial Intelligence. He is a Fellow of IEEE, a Fellow of EurAI, and a Fellow of IAPR. He was one the first people involved in European project on Artificial Intelligence CLAIRE, and he is currently a Fellow of Machine Learning association ELLIS. He is in the scientific committee of ICAR-CNR and is the President of the Scientific Committee of FBK-ICT. Professor Gori is currently holding an international 3IA Chair at the Université Cote d’Azur.