Dr. Xavier Hinaut, INRIA, Bordeaux gave a talk on Reservoir SMILES: Towards SensoriMotor Interaction of Language and Embodiment of Symbols with Reservoir Architectures on 23 January.
Here is the summary of Dr. Xavier Hinaut in his words:
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 work includes 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 aim to model general hierarchical sensorimotor processes; thus our models are not only relevant to language or vocal learning, but are interesting for a larger set of sensorimotor tasks. I will also present general results on reservoir computing, and why it is an interesting framework to model cognitive processes, like working memory for instance: extended reservoirs could gate information like GRU (Gated Recurrent Units).
Keywords: Reservoir Computing, Echo State Networks, Working Memory, Sensori-Motor, Perception-Action, Model, Robot, Sequences, Chunking, Symbol Emergence, Symbol Grounding Problem, Computational Neuroscience, Language Processing, Language Acquisition, Songbird, Sound Classification, Sound Generation.
Dr. Xavier Hinaut is a Research Scientist in Computational Neuroscience since 2016 at INRIA, Bordeaux, France. He received a MsC in Computer Science in 2008 from University of Technology of Compiègne, Compiègne, France and a MsC in Cognitive Science and AI in 2009 from École pratique des hautes études, Paris, France. He received a Ph.D in Computational Neuroscience from the University of Lyon in 2013, and received an Habilitation to Direct Researches (HDR) in Computer Science from the University of Bordeaux in 2022.
His work is at the frontier of neurosciences, machine learning, robotics, songbirds and linguistics: from the modelling of human sentence processing to the analysis of birdsongs and their neural correlates. It is mainly focussed on Recurrent Neural Network modelling (especially prefrontal cortex), language acquisition (applied to Robotics) and the brain codes of bird song syntax. The common thread is the neural coding and the modelling of complex sequence processing, “chunking,” learning and production, for “syntax-based” sequences, to be applied to robotics (for eventual embodiment). He manages the DeepPool ANR project on human sentence modelling with Reservoirs. He leads ReservoirPy development: a recent Python library for Reservoir Computing.