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 (, 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.

Master Thesis: “DaphneDSL implementation of Ion Beam Tuning Prediction in the context of DAPHNE” (EU funded project)

Job description
APC systems use internal sensors to continuously monitor semiconductor manufacturing processes and enable datadriven predictive maintenance. Your thesis focuses on ion implantation equipment, which requires ion beam tuning for every change in process specification. To avoid expensive timeouts due to unsuccessful tuning, an AI prediction model estimates the tuning outcome. Your main task is to enhance pre-existing Python code and transfer it into a newly developed Domain Specific Language with syntax similar to R, Julia and PyTorch.

In this work you will focus on developing DaphneDSL scripts for benchmarking purposes over the timeframe of 8 months.
Your tasks include:
• Study existing literature.
• Develop DaphneDSL scripts based on existing Python code.
• Perform benchmarking between Python and DaphneDSL implementations.
• Regular exchange with consortium members from 7 different nations of the EU funded DAPHNE project.
• Document your results by writing your master’s thesis.

Your Profile
You are a motivated Science, Technology, Engineering or Mathematics (STEM) student (f/m/div)*, with passion for computing and data. You are best equipped for this task if you have:
• Solid experience with Python (i.e., scikit-learn and TensorFlow/Keras).
• Fluent written and spoken English, German as a plus.

Expertise in the following areas is preferable – but not mandatory:
• C++, as this is the main language the DAPHNE framework is developed in. If there is an interest, contributions to the C++ code are also welcome.
• SQL, as this is the go-to way to query data from databases.

This position is subject to the collective agreement for workers and employees in the electrical and electronics industry (full-time), employment group D for master students (

Expected Start Date: 01. August 2023

Please attach the following documents (German or English) to your application:
• Motivation letter
• CV
• Certificate of matriculation at a university
• Latest Transcript of records (not older than 6 months)
• Highest completed educational certificate (Bachelor certificate for Master students)
• Reference letter (optional)

Send your application to: Andreas [dot] Laber [at] infineon [dot] com

Two kilometres of flight data: Publication of arguably the largest pool of real-world drone flight measurement data

Typically, drone flight data is generated under laboratory conditions – thus limiting its use for real-world application development. A team of researchers from Klagenfurt, working with two researchers from NASA’s Jet Propulsion Laboratory, has now published the first large pool of real-world measurement data. The data was generated in and around the Klagenfurt drone hall and in the context of the AMADEE20 Mars simulation in Israel.

Read more

Digitization Scholarship of the Province of Carinthia for Clara Josefine Hoestermann

Ms. Clara Josefine Hoestermann, B.A. MSc, was awarded the Digitalization Scholarship of the Province of Carinthia for her master’s thesis “Evaluating the potentials of Smart Technology in the context of patient wellbeing in hospital settings” supervised by Assoc.Prof. Mag. Dr. Gerhard Leitner, Department of Informatics Systems, Research Group Interactive Systems.

From 29 submitted scientific theses on the topic of digitization and its impact or significance for Carinthia, respectively three bachelor’s theses, diploma or master’s theses as well as dissertations were selected by a jury and honored by Governor Dr. Peter Kaiser during an award ceremony on November 23, 2022.
The Department of Informatics Systems congratulates Ms. Clara Josefine Hoestermann, B.A. MSc, warmly on the awarded scholarship!

See also:


Awarding of a digitization scholarship; LH Dr. Peter Kaiser, Clara Josefine Hoestermann and Univ.-Prof. Dr. Ralf Terlutter, Author: LPD Carinthia/Krainz