Keynote/Lecture 20 June 2022:
Prof. Ole-Christoffer Granmo is the Founding Director of the Centre for Artificial Intelligence Research (CAIR), University of Agder, Norway. He obtained his master’s degree in 1999 and the PhD degree in 2004, both from the University of Oslo, Norway, and created the Tsetlin machine in 2018. Dr. Granmo has authored more than 150 refereed papers with six best paper awards within machine learning, encompassing learning automata, bandit algorithms, Tsetlin machines, Bayesian reasoning, reinforcement learning, and computational linguistics. He has further coordinated 7+ research projects and graduated 55+ master- and eight PhD students. Dr. Granmo is also a co-founder of the Norwegian Artificial Intelligence Consortium (NORA). Apart from his academic endeavours, he co-founded the company Anzyz Technologies AS.
Title of talk: The Tsetlin Machine Today and Tomorrow
Keynote Speaker 20 June 2022:
Nikolaos Sidiropoulos, Louis T. Rader Professor and Chair, Department of Electrical & Computer Engineering, University of Virginia, USA.
N. Sidiropoulos is the Louis T. Rader Professor of Electrical and Computer Engineering at the University of Virginia. He earned his Ph.D. in Electrical Engineering from the University of Maryland–College Park, in 1992. He has served on the faculty of the University of Minnesota, and the Technical University of Crete, Greece. His research interests are in signal processing, communications, optimization, tensor decomposition, and factor analysis, with applications in machine learning and communications. He received the NSF/CAREER award in 1998, the IEEE Signal Processing Society (SPS) Best Paper Award in 2001, 2007, and 2011, and his students received four IEEE SPS conference best paper awards. Sidiropoulos has authored a Google Classic Paper in Signal Processing (on multicast beamforming), and his tutorial on tensor decomposition is ranked #1 in Google Scholar metrics for IEEE Transactions in Signal Processing (TSP), and tops the charts of the most popular / most frequently accessed TSP papers in IEEExplore. He served as IEEE SPS Distinguished Lecturer (2008-2009), Vice President of IEEE SPS (2017-2019), and chair of the IEEE Fellow evaluation committee of SPS (2020-2021). He received the 2010 IEEE Signal Processing Society Meritorious Service Award, and the 2013 Distinguished Alumni Award from the ECE Department of the University of Maryland. He is a Fellow of IEEE (2009) and a Fellow of EURASIP (2014). More information at http://www.ece.virginia.edu/~nds5j/ and https://scholar.google.com/citations?user=ZOkfkFMAAAAJ&hl=en
Title of talk: Learning as tensor completion
Abstract: Function approximation from input and output data pairs constitutes a fundamental problem in supervised learning. Deep neural networks are currently the most popular method for this task, but they are not interpretable and they do not work well with limited training. Tsetlin machines learn logical clauses from the input-output data, which is more parsimonious and interpretable. In this work, I will explain that identifying a general nonlinear function y=ƒ (x_1, …, x_N) of categorical (e.g., binary) variables x_1, …, x_N from input-output examples can be viewed as a tensor completion problem. This is important because provably correct nonlinear function identification is possible in this way, under certain reasonable conditions. Furthermore, I will explain how to extend this approach to the case of multivariate functions of continuous variables, which are not tensors in their native form. I will illustrate how well this idea works, even with limited training data, using various real-world classification tasks. Time permitting, I will provide a sneak preview of recent work (joint with Vladimir Zadorozhny) on interpretability.
References:
Nonlinear System Identification via Tensor Completion
N Kargas, ND Sidiropoulos, Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
Supervised learning and canonical decomposition of multivariate functions
N Kargas, ND Sidiropoulos, IEEE Transactions on Signal Processing 69, 1097-1107
Keynote Speaker 21 June 2022:
Dr. Veronique Ventos, Founding Head of Research, NukkAI and professor at University Paris Saclay.
Dr Véronique Ventos has a PhD in Artificial Intelligence and was an Associate Professor at Paris-Sud University where she investigated Logical Knowledge Representation and Symbolic Machine Learning. She is also a world reference in the field of AI applied to games.
In 2018 she cofounded NukkAI http://www.nukk.ai where as Head of Research she leads research on hybrid AI. NukkAI is committed to creating new generation AIs at the service of humans instead of replacing them and uses as a sandbox the game of Bridge which has resisted AI so far, unlike chess or Go.
In 2020 Forbes ranked Veronique Ventos 3rd woman defining the 21st Century AI movement
In 2022 her team achieved a major scientific breakthrough when Nook, the hybrid explainable AI designed by NukkAI, beat 8 world champions at a Bridge challenge that took place in Paris.
Title of talk: Nook: a new generation AI dedicated to the game of Bridge
Abstract: On March 25 2022, at the end of a two-day Bridge tournament against eight world champions the Bridge AI Nook was declared victorious. This is a world première the game of bridge still being a great challenge to Artificial Intelligence.
NooK is a new generation AI according to several aspects. The first one is related to the fact that Nook is hybrid since it is made up of symbolic rule-based modules and neural network one. Rather than learning by playing a huge amount of games, it begins by recovering and modeling human expertise in a Background Knowledge described using a relational logic. Moreover Nook is able to provide explanations related to each decision.
The robot is developed by NukkAI, a French start-up that we will present at the start of the talk. In the following we will give the basics of the game of bridge and its distinguishing characteristics from other mind games The other two parts will be devoted to the challenge and the description of the NooK modules.