spiking neural networks
For my Master of Science degree I did research on Spiking (or Pulsed) Neural Networks (SNNs). Like other artificial neural network paradigms, SNNs model a group of connected biological neurons, as found in neural tissue (see this site on the simulation of SNNs or Wikipedia for an explanation of this model).
In my master thesis I develop an extension of the existing learning method called SpikeProp so that it can handle multiple spikes per neuron.
For the experiments I had to implement a simulator for spiking neural networks. This resulted in some nice methods for efficient simulation of snns.
I hope to pick up on SNN soon, re-implementing SpikeProp and the simulator, focussing on recurrent networks...