Synapses

Implement static and plastic binary synapses

A synapse object should implement three methods:

  • A __call__ method taking an arbitrary number of inputs and returning the synapse output

  • An update(xo) method that passes the output of the neurons

  • A reset() method

Update and reset can be dummies, but a SpikingNet object expects that they will be implemented.

class spikelearn.synapses.BaseSynapse(Ne, No, W0, transform=None, learning_rule=None, syn_type=None)

Base class for a synapse.

Parameters:

  • Ne – dimensions of presynaptic neurons

  • No – dimensions of postsynaptic neurons

  • transform – input transform

  • syn_type – type of synapse, one of exc, inh, hybrid, None

property W

Returns the synaptic weights

class spikelearn.synapses.OneToOneSynapse(Ne, W0, transform=None, learning_rule=None, syn_type=None)

One to one static synapse

Implement one to one static synapse chaining each input to its corresponding output.

Parameters:

  • Ne – Dimensions of neurons in the layer

  • W0 – Synaptic weights

  • transform – input transform

  • syn_type – type of synapse, one of exc, inh, hybrid, None

class spikelearn.synapses.STDPSynapse(Ne, No, W0, tre, tro, transform=None, rule_params=None, Wlim=1, syn_type=None, tracelim=10)
class spikelearn.synapses.StaticSynapse(Ne, No, W0, transform=None, syn_type=None)

Base class for a synapse where synaptic weights are stored in a 2D array.

Parameters:

  • Ne – number of presynaptic neurons

  • No – number of postsynaptic neurons

  • W0 – a 2D array with the initial synaptic weights

  • transform – input transform

  • syn_type – type of synapse, one of exc, inh, hybrid, None