{"id":15700777,"url":"https://github.com/zimmerrol/spiking-bayesian-networks","last_synced_at":"2025-05-12T14:27:46.796Z","repository":{"id":98201823,"uuid":"171290166","full_name":"zimmerrol/spiking-bayesian-networks","owner":"zimmerrol","description":"Implementation of the paper Homeostatic plasticity in Bayesian spiking networks as Expectation Maximization with posterior constraints by Habenschuss et al.","archived":false,"fork":false,"pushed_at":"2019-04-21T19:58:55.000Z","size":17360,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-26T12:38:01.635Z","etag":null,"topics":["bayesian-inference","bayesian-spiking-neural-network","neural-network","nips","spiking-neural-networks"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zimmerrol.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-02-18T13:33:42.000Z","updated_at":"2023-11-20T09:55:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"6c1492ad-30e2-40c0-b93e-796a58ebb318","html_url":"https://github.com/zimmerrol/spiking-bayesian-networks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zimmerrol%2Fspiking-bayesian-networks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zimmerrol%2Fspiking-bayesian-networks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zimmerrol%2Fspiking-bayesian-networks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zimmerrol%2Fspiking-bayesian-networks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zimmerrol","download_url":"https://codeload.github.com/zimmerrol/spiking-bayesian-networks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243151005,"owners_count":20244493,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bayesian-inference","bayesian-spiking-neural-network","neural-network","nips","spiking-neural-networks"],"created_at":"2024-10-03T19:53:52.106Z","updated_at":"2025-03-12T03:31:27.281Z","avatar_url":"https://github.com/zimmerrol.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Implementation of the paper [Homeostatic plasticity in Bayesian spiking networks as Expectation Maximization with posterior constraints](https://papers.nips.cc/paper/4593-homeostatic-plasticity-in-bayesian-spiking-networks-as-expectation-maximization-with-posterior-constraints) by Habenschuss et al. This paper gives learning rules for a spiking neural network just based on Bayesian reasoning; therefore, the method can be used for unsupervised training of networks.\n\nContains code to runs different experiments on the proposed model and also on a model that is based not on a Binomial but Gaussian input distribution.\n\nThe code was written and the experiments conducted during a one week lasting seminar at the Max-Planck Institute for Dynamics and Self-Organization in 2019.\n\n# Key insights\n* `eta_b` has to be sufficiently large, otherwise homeostasis is not strong enough to keep `r` similar for all output neurons\n* Even though the paper claims that a factor of 10 between the learning rates is sufficient, we find out that `A_k(V)` contributes exponentially while `b_k` contributes only linearly. Therefore, a factor of ten between `eta_V` and `eta_b` is not always optimal.\n* Too few neurons for causes lead to learning of superposition states\n* Network can reconstruct images is was not trained on\n\nWhen images of digits between zero and five with the same ratio are shown to a network with 12 output neurons, for each class two neurons that are class-receptive arise. The neurons slowly learn to react to one of the input types.\n![Visualization of the learning process](https://github.com/FlashTek/spiking-bayesian-networks/raw/master/weights.gif)\n\n![Visualization of the learning process](https://github.com/FlashTek/spiking-bayesian-networks/raw/master/weights_pca.gif)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzimmerrol%2Fspiking-bayesian-networks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzimmerrol%2Fspiking-bayesian-networks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzimmerrol%2Fspiking-bayesian-networks/lists"}