Spiking Networks
- There are a lot of models of biological neurons, but it seems that all
neurons spike. That is, they collect energy, and if they get enough,
they spike, and send energy to (or take it away from) other neurons.
- We use PyNN for middleware and NEST as a neural simulator.
- We use a standard leaky integrate and fire neuron model.
- We use a standard STDP synaptic model.
- Both come with the standard PyNN and NEST systems.
- We build our own topologies and input regimes in PyNN.
- We use spikes of the "output" neurons to categorise.
- STDP works by the timing of the firing of the pre and post synaptic
neurons.
- If the presynaptic neuron fires first, the weight increases,
and if the post synaptic neuron is first the weight decreases.
