Friday Lunch Seminar: Yuji Kawai: “Learning model of motor timing and patterns using a modular random neural network” (On-line for CiNet members only: Sign-up required)

Friday Lunch Seminar (English)

May 20, 2022
12:15 〜 13:00

Talk Title: Learning model of motor timing and patterns using a modular random neural network

Yuji Kawai
Specially Appointed Associate Professor
Symbiotic Intelligent Systems Research Center
Institute for Open and Transdisciplinary Research Initiatives
Osaka University

Host PI: Minoru Asada

The ability of the brain to generate complex spatiotemporal patterns with a specific timing is essential for motor learning and time series prediction. An approach that tries to replicate this ability using the self-sustained neural activity of a randomly connected recurrent neural network (RNN), i.e., reservoir, meets the difficulty of orbital instability. We proposed a novel model that learns an arbitrary time series as the linear sum of stable trajectories produced by a large number of small random RNN modules. Our experimental results show that the trajectories of the module outputs are orthogonal to each other, that is, the reservoir self-organizes an orthogonal basis, that enables the model to learn the timing of extremely long intervals and complex time series of Lorenz system.