eprop_learning_signal_connection – Synapse model transmitting feedback learning signals for e-prop plasticity

Description

eprop_learning_signal_connection is an implementation of a feedback connector from eprop_readout readout neurons to eprop_iaf or eprop_iaf_adapt recurrent neurons that transmits the learning signals \(L_j^t\) for eligibility propagation (e-prop) plasticity and has a static weight \(B_{jk}\).

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

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

• eprop_iaf

• eprop_iaf_adapt

• eprop_readout

• eprop_synapse

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

Parameters

The following parameters can be set in the status dictionary.

Individual synapse parameters
Parameter	Unit	Math equivalent	Default	Description
delay	ms	\(d_{jk}\)	1.0	Dendritic delay
weight	pA	\(B_{jk}\)	1.0	Synaptic weight

Recordables

The following variables can be recorded. Note that since this connection lacks a plasticity mechanism the weight does not evolve over time.

Synapse recordables
State variable	Unit	Math equivalent	Initial value	Description
weight	pA	\(B_{jk}\)	1.0	Synaptic weight

Usage

This model can only be used in combination with the other e-prop models and 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

LearningSignalConnectionEvent

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, Plesser HE, Dahmen D, Bolten M, Van Albada SJ, Diesmann M. Event-based implementation of eligibility propagation (in preparation)

See also

Examples using this model

• Tutorial on learning N-MNIST classification with e-prop

• Tutorial on learning to accumulate evidence with e-prop after Bellec et al. (2020)

• Tutorial on learning to generate a lemniscate with e-prop after Bellec et al. (2020)

• Tutorial on learning to generate handwritten text with e-prop after Bellec et al. (2020)

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

• Tutorial on learning to generate sine waves with e-prop after Bellec et al. (2020)