Loading…
CNS*2020 Online has ended
Welcome to the Sched instance for CNS*2020 Online! Please read the instruction document on detailed information on CNS*2020.
Back To Schedule
Monday, July 20 • 7:00pm - 8:00pm
P71: Local homeostatic regulation of the spectral radius of echo-state networks

Log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
ZOOM LINK:

https://uni-frankfurt.zoom.us/j/96438263549?pwd=Zm8rVWZ3YjZRWjVuUzNKWTRJaUFMUT09

Password: 196137


Fabian Schubert, Claudius Gros
Recurrent cortical network dynamics plays a crucial role for sequential information processing in the brain. While the theoretical framework of reservoir computing provides a conceptual basis for the understanding of recurrent neural computation, it often requires manual adjustments of global network parameters, in particular of the spectral radius of the recurrent synaptic weight matrix. Being a mathematical and relatively complex quantity, the spectral radius is not readily accessible to biological neural networks, which are based on the principle that information about the network state should either be encoded in local intrinsic dynamical quantities (e.g. membrane potentials), or transmitted via synaptic connectivity. We present an intrinsic adaptation rule, termed _flow control_ , for echo state networks that solely relies on locally accessible variables, while still being capable of tuning a global quantity, the spectral radius of the network, towards a desired value. The adaptation rule works online, in the presence of a continuous stream of input signals. It is based on a local comparison between the mean squared recurrent membrane potential and the mean squared activity of the neuron itself. It is derived from a global scaling condition on the dynamic flow of neural activities, and requires the separability between external and recurrent input currents. The effectiveness of the presented mechanism is tested numerically using different external input protocols. Furthermore, the network performance after applying the adaptation is evaluated by training the network to perform a time delayed XOR operation on binary sequences.

Speakers
FS

Fabian Schubert

Institute for Theoretical Physics, Goethe University Frankfurt



Monday July 20, 2020 7:00pm - 8:00pm CEST
Slot 17