Conférence spéciale de la Fondation IPSEN au colloque NeuroFrance

Conférence spéciale de la Fondation IPSEN au colloque NeuroFrance

15 mai 2017

Conférence spéciale de la Fondation IPSEN au colloque NeuroFrance

Lors du prochain colloque NeuroFrance, qui se tiendra à Bordeaux du 17 au 19 mai prochain, la Fondation IPSEN organise une conférence spéciale "Brain and Machine Learning and Memory". Hughes Bersini (Laboratoire IRIDIA, Université Libre de Bruxelles, Belgique) et Paul Frankland (Hospital for Sick Children, Toronto, Canada), par leur conférence respective, permettront de faire le parallèle entre l'homme et la machine sur ces questions d'apprentissage et de mémorisation (Mercredi 17 mai, à partir de 17h30, Amphithéâtre A).

Hughes Bersini, 17h30 à 18h15, Conscious and unconscious Artificial Intelligence

I will first briefly discuss how since the birth of AI two traditions have always been very productive, labelled for simplicity “conscious and unconscious”, then how and why the second one, based on Big Data and Machine Learning, is dangerously taking the lead today. Thus I will discuss what more recent researches in neural networks such as deep learning (deep in space and time), self-adapting nets and chaotic Hopfield networks might bring to neurosciences.

Paul Frankland, 18h15 à 19h, The Persistance and Transience of Memory

The predominant focus in the neurobiological study of memory has been on remembering (persistence). However, recent studies have considered the neurobiology of forgetting (transience). In my talk I will draw parallels between neurobiological and computational mechanisms underlying transience. I will propose that it is the interaction between persistence and transience that allows for intelligent decision-making in dynamic, noisy environments. Specifically, I will argue that transience (1) enhances flexibility, by reducing the influence of outdated information on memory-guided decision making, and (2) prevents overfitting to specific past events, thereby promoting generalization. According to this view, the goal of memory is not the transmission of information through time, per se. Rather, the goal of memory is to optimize decision-making. As such, transience is as important as persistence in mnemonic systems.

Document: Flyer de la conférence spéciale