Pulsed Neural Networks
Sparse distributed memory using N-of-M codes
Neural Networks
Hi-index | 0.00 |
In this paper we examine issues involving the transmission of information by spike trains through networks made of real time asynchronous spiking neurons. For our convenience we use a spiking model that is has an intrinsic delay between an input and output spike. We look at issues involving transmission of a desired average level of stable spiking activity over many layers, and show how feed-back reset inhibition can achieve this aim. We then deal with the coherence of spike trains and show that it is possible for a burst of spikes emitted by a layer to not diverge when passing through different layers of neurons. We present the results of simulations done on a multi layered feed-forward system to illustrate our method.