Evolving Spiking Neural Networks for Nonlinear Control Problems
This work addresses the challenge of applying spiking neural networks to continuous control problems, which is incremental as it builds on existing topology evolution methods.
The paper tackled nonlinear control problems by developing a recurrent spiking neural network controller that uses topology evolution for learning, achieving significantly faster learning speeds compared to sigmoidal neural networks in a classic control task.
Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been non-behavioural and discontinuous. Comparatively, this paper presents a recurrent spiking controller that is capable of solving nonlinear control problems in continuous domains using a popular topology evolution algorithm as the learning mechanism. We propose two mechanisms necessary to the decoding of continuous signals from discrete spike transmission: (i) a background current component to maintain frequency sufficiency for spike rate decoding, and (ii) a general network structure that derives strength from topology evolution. We demonstrate that the proposed spiking controller can learn significantly faster to discover functional solutions than sigmoidal neural networks in solving a classic nonlinear control problem.