[DL] [AIxIA] Spotlight Seminar on AI - MARCO GORI - April 29 2024 - link

[Luciano Serafini]

[* Apologies in case of multiple posting *]

The Italian Association for Artificial Intelligence, in collaboration with the AISB (Society for the Study of Artificial Intelligence and Simulation of Behaviour, UK) is pleased to announce the next seminar of its Spotlight Seminars on AI initiative:

April, 29 – 5:00PM (CET)
Title: Consciousness and the Laws of Learning 
Speaker: MARCO GORI, University of Siena 

Link:
https://www.youtube.com/watch?v=ti0uPvIwyDM

The fields of Artificial Intelligence (AI) and Cognitive Science began crossing their paths significantly during the Eighties when the Connectionist wave strongly pushed the studies on Artificial Neural Networks. The evolution of the last decades in AI with the focus on deep learning and, recently, on generative AI, has been producing spectacular results that were hardly predictable even by the fathers of the discipline. However, when looking at early studies on Connectionism, most dreams are still waiting to be realized, since most successful results rely on the brute force coming from joining computational resources and large data collections. This is far away from what we observe in Nature, where cognition emerges simply from environmental interactions while processing temporal information. In order to capture those natural processes and prospect an alternative path to Machine Learning, in this talk I give a preliminary view of cognitive systems whose environmental interactions are dictated by genetic features that are translated into the minimization of an objective functional over time. This functional, that is referred to as the cognitive action of the system, replaces the classic Machine Learning statistical functional risk. I use the apparatus of Theoretical Physics and Optimal Control to derive unified laws of cognition for learning and inference and show that Hamiltonian
equations in their causal dissipative form approximate the optimal solution over the entire data collection of the agent life. This comes from imposing the evolution on a Hamiltonian track which gives rise to a computational scheme for both focus of attention and conscious actions.

Bio:  Marco Gori is full professor of computer science at the University of Siena and 3IA chair at Université Côte d’Azur, Nice (MAASAI lab https://team.inria.fr/maasai/team-members/ <https://www.google.com/url?q=https://team.inria.fr/maasai/team-members/&source=gmail-imap&ust=1714471453000000&usg=AOvVaw3bmIIga2N9abJgpVLrynl2>).  His research interests are in the field of artificial intelligence, with emphasis on machine learning, vision, and game playing. In the last few years, he has been mainly involved in the unification of computational processes of reasoning and learning, driven by the principle that the the emergence of cognition is rooted in natural laws of computation.  He also very much like discussions on novel models of computation and their relationships with human brain.

The joint AI*IA/AISB Committee of the Spotlight Seminars on AI, 

Giuseppe De Giacomo
Floriana Grasso
Antonio Lieto
Bertie Muller
Luciano Serafini

-- 

-- 
--
Le informazioni contenute nella presente comunicazione sono di natura 
privata e come tali sono da considerarsi riservate ed indirizzate 
esclusivamente ai destinatari indicati e per le finalità strettamente 
legate al relativo contenuto. Se avete ricevuto questo messaggio per 
errore, vi preghiamo di eliminarlo e di inviare una comunicazione 
all’indirizzo e-mail del mittente.

--
The information transmitted is 
intended only for the person or entity to which it is addressed and may 
contain confidential and/or privileged material. If you received this in 
error, please contact the sender and delete the material.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.zih.tu-dresden.de/pipermail/dl/attachments/20240423/6674ae23/attachment-0001.htm>