Spiking neural networks

Spiking neural networks are instantiated using the SpikingNet class. A SpikeNet contains layers, synapses, and inputs.

class spikelearn.snn.SpikingNet

A class implementing arbitrary neural networks

Instances start with empty networks, which can be subsequently populated with layers, inputs, and synapses

  • Layers are objects taking a one or more inputs and returning an output. They should implement the methods __call__ and reset and an attribute out that preserves the results from the last computation.

  • Inputs define external inputs whose values are passed to the network through the __call__ method.

  • Synapses connect one or more presynaptic layers with a postsynaptic layer. They should implement the methods __call__, reset, and update. The update method should be able to take two arguments, one representing the activity of the postsynaptic neuron and an optional flag that triggers learning if it is an active synapse.

A network can be constructed using a series of method that help define inputs, outputs, layers, and the synapses connecting them. The construction of the network is meant to be a one-off process. Deleting layers or synapses would most likely break the network or result in unpredictable behavior.

__call__(*args, learn=True)

Advances the network a single timestep.

Parameters:

  • args – a tuple of inputs. Must match the number of inputs in the SpikingNet object

  • learn – if True, broadcasts a learn signal at the end of the timestep

Returns:

A list with the declared network outputs

add_input(name)

Adds an external input

Parameters:

name – the name of the input

Raises:

ValueError – User tries to reuse an existing name

add_layer(snl, name)

Adds a layer to the snn

Parameters:

  • snl – a layer of neurons

  • name – the name of the layer

add_output(name, n=1)

Defines an output

Parameters:

  • name – name of the layer

  • n – index of the element output to be returned (optional, default 1)

add_synapse(pos_name, syn, *pre_names)

Adds a synapse between two or more network nodes

A synapse has only one postsynaptic connection but can have more than one presynaptic connection to include the case of ternary synapses involving one or more modulatory inputs.

Parameters:

  • pos_name – name of the postsynaptic layer

  • syn – a synapse object

  • pre_names – names of one or more presynaptic layers

Raises:

ValueError – pre or postsynaptic connection not identified.

reset()

Broadcasts a reset signal to all layers and synapses in the network

update(learn)

Broadcasts a learn signal to all layers and synapses