Xavier Hinaut presents Sensorimotor Interaction of Language and Embodiment of Symbols with Reservoir Architectures

On 2022-12-01 11:00:00 at G102A, Karlovo náměstí 13, Praha 2
*Room: E218*

Full title: Reservoir SMILES: Towards SensoriMotor Interaction of Language and
Embodiment of Symbols with Reservoir Architectures

Abstract: Language involves several hierarchical levels of abstraction. Most
models focus on a particular level of abstraction making them unable to model
bottom-up and top-down processes. Moreover, we do not know how the brain
grounds
symbols to perceptions and how these symbols emerge throughout development.
Experimental evidence suggests that perception and action shape one-another
(e.g. motor areas activated during speech perception) but the precise
mechanisms
involved in this action-perception shaping at various levels of abstraction are
still largely unknown.

My previous and current work include the modelling of language comprehension,
language acquisition with a robotic perspective, sensorimotor models and
extended models of Reservoir Computing to model working memory and hierarchical
processing. I propose to create a new generation of neural-based computational
models of language processing and production; to use biologically plausible
learning mechanisms relying on recurrent neural networks; create novel
sensorimotor mechanisms to account for action-perception shaping; build
hierarchical models from sensorimotor to sentence level; embody such models in
robots.

I am to model general hierarchical sensorimotor processes, thus we expect that
the kind of models we develop are not only relevant to language or vocal
learning, but are interesting for a large set of sensorimotor tasks. I will
also
talk about general results on reservoir computing, and why it is an interesting
framework to model cognitive processes, like working memory for instance. We
will see that extended reservoirs could gate information like GRU (Gated
Recurrent Units).
Responsible person: Petr Pošík