Excitable Networks for Finite State Computation with Continuous Time Recurrent Neural Networks
From MaRDI portal
Publication:6355520
DOI10.1007/S00422-021-00895-5arXiv2012.04129MaRDI QIDQ6355520
Peter Ashwin, Claire Postlethwaite
Publication date: 7 December 2020
Abstract: Continuous time recurrent neural networks (CTRNN) are systems of coupled ordinary differential equations that are simple enough to be insightful for describing learning and computation, from both biological and machine learning viewpoints. We describe a direct constructive method of realising finite state input-dependent computations on an arbitrary directed graph. The constructed system has an excitable network attractor whose dynamics we illustrate with a number of examples. The resulting CTRNN has intermittent dynamics: trajectories spend long periods of time close to steady-state, with rapid transitions between states. Depending on parameters, transitions between states can either be excitable (inputs or noise needs to exceed a threshold to induce the transition), or spontaneous (transitions occur without input or noise). In the excitable case, we show the threshold for excitability can be made arbitrarily sensitive.
This page was built for publication: Excitable Networks for Finite State Computation with Continuous Time Recurrent Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6355520)
