eprop_synapse_bsshslm_2020 – Synapse type for e-prop plasticity

Description

eprop_synapse_bsshslm_2020 is an implementation of a connector model to create synapses between postsynaptic neurons \(j\) and presynaptic neurons \(i\) for eligibility propagation (e-prop) plasticity.

E-prop plasticity was originally introduced and implemented in TensorFlow in [1].

The suffix _bsshslm_2020 follows the NEST convention to indicate in the model name the paper that introduced it by the first letter of the authors’ last names and the publication year.

The e-prop synapse collects the presynaptic spikes needed for calculating the weight update. When it is time to update, it triggers the calculation of the gradient which is specific to the post-synaptic neuron and is thus defined there.

Eventually, it optimizes the weight with the specified optimizer.

E-prop synapses require archiving of continuous quantities. Therefore e-prop synapses can only be connected to neuron models that are capable of archiving. So far, compatible models are eprop_iaf_bsshslm_2020, eprop_iaf_adapt_bsshslm_2020, and eprop_readout_bsshslm_2020.

For more information on e-prop plasticity, see the documentation on the other e-prop models:

• eprop_iaf_bsshslm_2020

• eprop_iaf_adapt_bsshslm_2020

• eprop_readout_bsshslm_2020

• eprop_learning_signal_connection_bsshslm_2020

For more information on the optimizers, see the documentation of the weight optimizer:

• weight_optimizer

Details on the event-based NEST implementation of e-prop can be found in [2].

Warning

This synaptic plasticity rule does not take precise spike timing into account. When calculating the weight update, the precise spike time part of the timestamp is ignored.

Parameters

The following parameters can be set in the status dictionary.

Common synapse parameters
Parameter	Unit	Math equivalent	Default	Description
average_gradient	Boolean		False	If True, average the gradient over the learning window
optimizer			{}	Dictionary of optimizer parameters

Individual synapse parameters
Parameter	Unit	Math equivalent	Default	Description
delay	ms	\(d_{ji}\)	1.0	Dendritic delay
tau_m_readout	ms	\(\tau_\text{m,out}\)	10.0	Time constant for low-pass filtering of eligibility trace
weight	pA	\(W_{ji}\)	1.0	Initial value of synaptic weight

Recordables

The following variables can be recorded.

• synaptic weight weight

Usage

This model can only be used in combination with the other e-prop models, whereby the network architecture requires specific wiring, input, and output. The usage is demonstrated in several supervised regression and classification tasks reproducing among others the original proof-of-concept tasks in [1].

Transmits

SpikeEvent, DSSpikeEvent

References

[1] (1,2)

Bellec G, Scherr F, Subramoney F, Hajek E, Salaj D, Legenstein R, Maass W (2020). A solution to the learning dilemma for recurrent networks of spiking neurons. Nature Communications, 11:3625. https://doi.org/10.1038/s41467-020-17236-y

[2]

Korcsak-Gorzo A, Stapmanns J, Espinoza Valverde JA, Dahmen D, van Albada SJ, Bolten M, Diesmann M. Event-based implementation of eligibility propagation (in preparation)

See also

Examples using this model

• Tutorial on learning to accumulate evidence with e-prop

• Tutorial on learning to generate an infinite loop with e-prop

• Tutorial on learning to generate handwritten text with e-prop

• Tutorial on learning to generate sine waves with e-prop