Closed-form control with spike coding networks

by   Filip S. Slijkhuis, et al.

Efficient and robust control using spiking neural networks (SNNs) is still an open problem. Whilst behaviour of biological agents is produced through sparse and irregular spiking patterns, which provide both robust and efficient control, the activity patterns in most artificial spiking neural networks used for control are dense and regular – resulting in potentially less efficient codes. Additionally, for most existing control solutions network training or optimization is necessary, even for fully identified systems, complicating their implementation in on-chip low-power solutions. The neuroscience theory of Spike Coding Networks (SCNs) offers a fully analytical solution for implementing dynamical systems in recurrent spiking neural networks – while maintaining irregular, sparse, and robust spiking activity – but it's not clear how to directly apply it to control problems. Here, we extend SCN theory by incorporating closed-form optimal estimation and control. The resulting networks work as a spiking equivalent of a linear-quadratic-Gaussian controller. We demonstrate robust spiking control of simulated spring-mass-damper and cart-pole systems, in the face of several perturbations, including input- and system-noise, system disturbances, and neural silencing. As our approach does not need learning or optimization, it offers opportunities for deploying fast and efficient task-specific on-chip spiking controllers with biologically realistic activity.


page 1

page 7


Towards neuromorphic control: A spiking neural network based PID controller for UAV

In this work, we present a spiking neural network (SNN) based PID contro...

A Bin Encoding Training of a Spiking Neural Network-based Voice Activity Detection

Advances of deep learning for Artificial Neural Networks(ANNs) have led ...

Nonlinear computations in spiking neural networks through multiplicative synapses

The brain performs many nonlinear computations through intricate spiking...

Fitting summary statistics of neural data with a differentiable spiking network simulator

Fitting network models to neural activity is becoming an important tool ...

Enabling hyperparameter optimization in sequential autoencoders for spiking neural data

Continuing advances in neural interfaces have enabled simultaneous monit...

A Spiking Network that Learns to Extract Spike Signatures from Speech Signals

Spiking neural networks (SNNs) with adaptive synapses reflect core prope...

Please sign up or login with your details

Forgot password? Click here to reset