Invitation Talk: “Towards Large Neural Networks that can Reason”

The Italian Association for Artificial Intelligence is pleased to announce the next seminar of its Spotlight Seminars on AI initiative:

April, 20 – 5:00PM (CEST)

Title: Towards Large Neural Networks that can Reason

Speaker: YOSHUA BENGIO, Université de Montréal

The aim of the seminar series is to illustrate, explore and discuss current scientific challenges, trends, and possibilities in all branches of our articulated research field. The seminars will be held virtually on the YouTube channel of the Association (https://www.youtube.com/c/AIxIAit), on a monthly basis (and made permanently available on that channel), by leading Italian researchers as well as by top international scientists.

The seminars are mainly aimed at a broad audience interested in AI research, and they are also included in the Italian PhD programme in Artificial Intelligence; indeed, AIxIA warmly encourages the attendance of young scientists and PhD students.

Bio: Yoshua Bengio is recognized worldwide as one of the leading experts in artificial intelligence, known for his conceptual and engineering breakthroughs in artificial neural networks and deep learning. He is a Full Professor in the Department of Computer Science and Operations Research at Université de Montréal and the Founder and Scientific Director of Mila – Quebec Artificial Intelligence Institute, one of the largest academic institutes in deep learning and one of the three federally-funded centers of excellence in AI research and innovation in Canada. He began his studies in Montreal, where he obtained his Ph.D. in Computer Science from McGill University in 1992. After completing a postdoctoral fellowship at the Massachusetts Institute of Technology (MIT) on statistical learning and sequential data, he completed a second postdoc at AT&T Bell Laboratories, in Holmdel, NJ, on learning and vision algorithms in 1993. That same year, he returned to Montreal and joined UdeM as a faculty member. In 2016, he became the Scientific Director of IVADO. He is Co-Director of the CIFAR Learning in Machines & Brains program that funded the initial breakthroughs in deep learning and since 2019, holds a Canada CIFAR AI Chair and is Co-Chair of Canada’s Advisory Council on AI. In 2022, Yoshua Bengio became the most cited computer scientist in the world (h-index). Concerned about the social impact of AI, he actively took part in the conception of the Montreal Declaration for the Responsible Development of Artificial Intelligence. His goal is to contribute to uncovering the principles giving rise to intelligence through learning while favouring the development of AI for the benefit of all. Yoshua Bengio was made an Officer of the Order of Canada and a Fellow of the Royal Society of Canada in 2017 and in 2020, became a Fellow of the Royal Society of London. From 2000 to 2019, he held the Canada Research Chair in Statistical Learning Algorithms. He is a member of the NeurIPS Foundation advisory board and Co-Founder of the ICLR conference. His scientific contributions have earned him numerous awards, including the 2019 Killam Prize for Natural Sciences, the 2017 Government of Québec Marie-Victorin Award, the 2018 Lifetime Achievement Award from the Canadian AI Association, the Prix d’excellence FRQNT (2019), the Medal of the 50th Anniversary of the Ministry of International Relations and Francophonie (2018), the 2019 IEEE CIS Neural Networks Pioneer Award, Acfas’s Urgel-Archambault Prize (2009) and in 2017, he was named Radio-Canada’s Scientist of the Year. He is the 2018 laureate of the A.M. Turing Award, “the Nobel Prize of Computing,” alongside Geoffrey Hinton and Yann LeCun for their important contributions and advances in deep learning. In 2022, he was appointed Knight of the Legion of Honor by France and named co-laureate of Spain’s Princess of Asturias Award for technical and scientific research.

Abstract: Current neural networks, such as large language models and those based on images or paired images and text, are trained to fit their training data, with very little in their architecture that could force them to produce answers that are coherent with respect to individual pieces of knowledge. In that sense, they seem to be missing some of the reasoning abilities and causal understanding that humans can benefit from, and this may result in incoherent outputs and mistakes that humans would typically not make, especially out-of-distribution. This raises the larger question of how higher-level cognitive abilities could be incorporated in deep learning. We know a lot from neuroscience and cognitive science about them and that can be used to design new architectures and training frameworks with the corresponding inductive biases. This has motivated a novel form of deep learning called generative flow networks or GFlowNets, borrowing from reinforcement learning, generative models and amortized variational inference. GFlowNets can sequentially generate compositional data structures whose content may be analogous to our thoughts, and they can be trained to sample them with probability proportional to some given or learned reward function that corresponds with the coherence of the context and generated answer with a structured world model. A GFlowNet can thus be trained to perform amortized probabilistic inference that is consistent with the pieces of knowledge of the world model, including in the sense of generating samples from a Bayesian posterior over world models. Like with amortized variational methods, this can be used to learn the world model itself. That arrangement is similar to model-based reinforcement learning (where we separate the policy from the world model) but concerns the learning of a policy that chooses what internal computation (i.e. reasoning) to perform, rather than acting in the world. Unlike with state-of-the-art deep learning and reinforcement learning, this makes it easy to incorporate inductive biases about high-level cognition and causality in the world model itself, such as sparse causal dependencies and reusable modular pieces of knowledge. It means that the GFlowNet probabilistic inference machine can be trained by querying the world model, without having to directly interact with the real world, and can be as large and trained with as many queries as our computational capabilities allow: unlike current deep nets, its effective capacity is not limited by the size of the externally observed data. This is convenient because probabilistic inference is generally intractable and may thus require high capacity in order to be approximated with a fast neural net. The mathematical foundations of GFlowNets and how they constitute an interesting ML-based alternative to MCMC inference will be briefly explained and recent work on GFlowNets highlighted.

Decoration of Honour of the Province of Carinthia for Univ.-Prof. Gerhard Friedrich

For his special services as a professor and in particular as the longstanding Dean of the Faculty of Technical Sciences at the University of Klagenfurt, Univ.-Prof. DI Dr. Gerhard Friedrich was awarded the Decoration of Honour of the Province of Carinthia by Governor Dr. Peter Kaiser on 18 July 2022 in the Mirror Hall of the Carinthian Provincial Government.

Mr Friedrich has worked persistently and highly successfully for a focus of Carinthia as an educational, scientific and business location in the field of technical sciences and digitalisation. Particularly noteworthy in this context is his great commitment in the field of artificial intelligence applications. In addition, he was able to successfully promote and expand networking between the Austrian economy and the University of Klagenfurt. Thanks to his initiative and tireless efforts, a significant expansion of the technical sciences in terms of personnel and content has been achieved, especially in the area of cybersecurity and modular robot systems.

During his tenure, among other things, the computer science workshop, the establishment of a drone hall, the establishment of the Silicon Austria Lab (SAL) and successful and promising cooperations with the research institution Joanneum Research, newly settled in Carinthia, were created. He has consistently pursued the orientation of the Faculty of Technical Sciences towards international visibility and scientific excellence, thus enabling highly gratifying results in the university rankings.

We warmly congratulate Univ.-Prof. Gerhard Friedrich!

 

Governor Peter Kaiser presents the Decoration of Honour of the Province of Carinthia to Gerhard Friedrich | Photo: LPD Kärnten/Eggenberger

Two research teams from the University of Klagenfurt remain in the running to be “Clusters of Excellence”

As recently announced by the Austrian Science Fund FWF, eleven teams have reached the final stage of selection for “Cluster of Excellence” funding. The decisions on Austria’s future beacons of basic research will be made in early 2023. The eleven consortia include the “Multi-drone Systems” cluster initiated and led by the University of Klagenfurt, as well as the “Bilateral Artificial Intelligence” project, which feature scientists from Klagenfurt on their Board of Directors.

Read more

Trends in Recommendations Systems – A Netflix Perspective

Thursday April 7th 2022 | 05.30 pm (CET) | via Zoom

Anuj Shah, Ph. D. | Senior Machine Learning Research Practitioner at Netflix |

Click here to register for the meeting:

https://zoom.us/meeting/register/tJYvdO-gqzMiEtKOfNIgcZAZOQ8jA3i_b3Pi

 

Abstract:

Recommendation systems today are widely used across many applications such as in multimedia content platforms, social networks, and ecommerce, to provide suggestions to users that are most likely to fulfill their needs, thereby improving the user experience. Academic research, to date, largely focuses on the performance of recommendation models in terms of ranking quality or accuracy measures, which often don’t directly translate into improvements in the real-world. In this talk, we present some of the most interesting challenges that we face in the personalization efforts at Netflix. The goal of this talk is to sunshine challenging research problems in industrial recommendation systems and start a conversation about exciting areas of future research.

 

Bio:

Anuj Shah is a Senior Machine Learning Research Practitioner at Netflix. For the past 10+ years, he’s been working on an applied research team focused on developing the next generation of algorithms used to generate the Netflix homepage through machine learning, ranking, recommendation, and large-scale software engineering. He is extremely passionate about algorithms and technologies that help improve the Netflix customer experience with highly personalized consumer-facing products like the Continue Watching row, the Top 10 rows amongst many others. Prior to Netflix, he worked on machine learning in the Computational Sciences Division at the Pacific Northwest National Laboratory focusing on technologies at the intersection of proteomics, bioinformatics and Computer Science for 8 years. He has a Ph.D. from the Computer Science department at Washington State University and a Masters in C.S. from Virginia Tech