A Memory-Based STDP Rule for Stable Attractor Dynamics in Boolean Recurrent Neural Networks

0503755 - ÚI 2020 RIV US eng C - Conference Paper (international conference)
Cabessa, Jérémie - Villa, A.
A Memory-Based STDP Rule for Stable Attractor Dynamics in Boolean Recurrent Neural Networks.
IJCNN 2019. International Joint Conference on Neural Networks Proceedings. New York: IEEE, 2019, č. článku N-20311. ISBN 978-1-7281-1985-4.
[IJCNN 2019. International Joint Conference on Neural Networks /32./. Budapest (HU), 14.07.2019-19.07.2019]
R&D Projects: GA ČR(CZ) GA19-05704S
Institutional support: RVO:67985807
Keywords : learning (artificial intelligence) * recurrent neural nets
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

We consider a simplified Boolean model of the basal ganglia-thalamocortical network, and study the effect of a spiketiming- dependent plasticity (STDP) rule on the stabilization ofits attractor dynamics. More precisely, we introduce an adaptive STDP rule which constantly updates its learning rate based on the attractors that the network encounters during a window of past time steps. This so-called network memory is assumed to be dynamic: its duration is step-wise increased every time a trigger input pattern is detected, and is decreased otherwise. In this context, we show that well-adjusted trigger inputs can fine tune the network memory and its associated STDP rule in such a way to drive the network into stable and rich attractor dynamics. We discuss how this feature might be related to reward learning processes in the neurobiological context
Permanent Link: http://hdl.handle.net/11104/0295541