Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks.
Learning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the optimal weight values can be posed as a supervised learning task...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0229083 |
| _version_ | 1818667160136843264 |
|---|---|
| author | Bryce Allen Bagley Blake Bordelon Benjamin Moseley Ralf Wessel |
| author_facet | Bryce Allen Bagley Blake Bordelon Benjamin Moseley Ralf Wessel |
| author_sort | Bryce Allen Bagley |
| collection | DOAJ |
| description | Learning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the optimal weight values can be posed as a supervised learning task wherein the weights of the model network are chosen to maximize the similarity between the target spike trains and the model outputs. It is still largely unknown whether optimizing spike train similarity of highly recurrent SNNs produces weight matrices similar to those of the ground truth model. To this end, we propose flexible heuristic supervised learning rules, termed Pre-Synaptic Pool Modification (PSPM), that rely on stochastic weight updates in order to produce spikes within a short window of the desired times and eliminate spikes outside of this window. PSPM improves spike train similarity for all-to-all SNNs and makes no assumption about the post-synaptic potential of the neurons or the structure of the network since no gradients are required. We test whether optimizing for spike train similarity entails the discovery of accurate weights and explore the relative contributions of local and homeostatic weight updates. Although PSPM improves similarity between spike trains, the learned weights often differ from the weights of the ground truth model, implying that connectome inference from spike data may require additional constraints on connectivity statistics. We also find that spike train similarity is sensitive to local updates, but other measures of network activity such as avalanche distributions, can be learned through synaptic homeostasis. |
| first_indexed | 2024-12-17T06:16:00Z |
| format | Article |
| id | doaj.art-fc54297a5b654bd19e7cdb2bef7c6891 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-17T06:16:00Z |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-fc54297a5b654bd19e7cdb2bef7c68912022-12-21T22:00:30ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01152e022908310.1371/journal.pone.0229083Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks.Bryce Allen BagleyBlake BordelonBenjamin MoseleyRalf WesselLearning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the optimal weight values can be posed as a supervised learning task wherein the weights of the model network are chosen to maximize the similarity between the target spike trains and the model outputs. It is still largely unknown whether optimizing spike train similarity of highly recurrent SNNs produces weight matrices similar to those of the ground truth model. To this end, we propose flexible heuristic supervised learning rules, termed Pre-Synaptic Pool Modification (PSPM), that rely on stochastic weight updates in order to produce spikes within a short window of the desired times and eliminate spikes outside of this window. PSPM improves spike train similarity for all-to-all SNNs and makes no assumption about the post-synaptic potential of the neurons or the structure of the network since no gradients are required. We test whether optimizing for spike train similarity entails the discovery of accurate weights and explore the relative contributions of local and homeostatic weight updates. Although PSPM improves similarity between spike trains, the learned weights often differ from the weights of the ground truth model, implying that connectome inference from spike data may require additional constraints on connectivity statistics. We also find that spike train similarity is sensitive to local updates, but other measures of network activity such as avalanche distributions, can be learned through synaptic homeostasis.https://doi.org/10.1371/journal.pone.0229083 |
| spellingShingle | Bryce Allen Bagley Blake Bordelon Benjamin Moseley Ralf Wessel Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. PLoS ONE |
| title | Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. |
| title_full | Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. |
| title_fullStr | Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. |
| title_full_unstemmed | Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. |
| title_short | Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks. |
| title_sort | pre synaptic pool modification pspm a supervised learning procedure for recurrent spiking neural networks |
| url | https://doi.org/10.1371/journal.pone.0229083 |
| work_keys_str_mv | AT bryceallenbagley presynapticpoolmodificationpspmasupervisedlearningprocedureforrecurrentspikingneuralnetworks AT blakebordelon presynapticpoolmodificationpspmasupervisedlearningprocedureforrecurrentspikingneuralnetworks AT benjaminmoseley presynapticpoolmodificationpspmasupervisedlearningprocedureforrecurrentspikingneuralnetworks AT ralfwessel presynapticpoolmodificationpspmasupervisedlearningprocedureforrecurrentspikingneuralnetworks |