{"id":16511255,"url":"https://github.com/pbenner/lisp-backprop","last_synced_at":"2026-03-18T20:07:57.509Z","repository":{"id":69897617,"uuid":"481855917","full_name":"pbenner/lisp-backprop","owner":"pbenner","description":"Old implementation of Backpropagation in Lisp","archived":false,"fork":false,"pushed_at":"2022-04-15T06:30:49.000Z","size":656,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-11-29T06:57:23.168Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Common Lisp","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pbenner.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2022-04-15T06:08:32.000Z","updated_at":"2025-04-30T17:49:11.000Z","dependencies_parsed_at":"2023-02-26T01:30:12.117Z","dependency_job_id":null,"html_url":"https://github.com/pbenner/lisp-backprop","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pbenner/lisp-backprop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pbenner%2Flisp-backprop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pbenner%2Flisp-backprop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pbenner%2Flisp-backprop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pbenner%2Flisp-backprop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pbenner","download_url":"https://codeload.github.com/pbenner/lisp-backprop/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pbenner%2Flisp-backprop/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30075922,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-04T08:01:56.766Z","status":"ssl_error","status_checked_at":"2026-03-04T08:00:42.919Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2024-10-11T15:59:31.401Z","updated_at":"2026-03-04T08:03:03.924Z","avatar_url":"https://github.com/pbenner.png","language":"Common Lisp","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Structure\n\n* src\n  * Source code of the backpropagation algorithm\n\n* data\n  * Training and validation sets\n\n* data/train\n  * Data set generated from two images\n\n* data/train2\n  * Data set generated from ten images\n\n* src/FourierMellin\n  * MATLAB source code of the Fourier-Mellin transform\n\n## How to generate the training set\n\nGo to *data/train* or *data/train2* and execute *./import2.pl*\n(edit the script to change the size of the data set).\n\nUse *src/FourierMellin/applyCavanagh.m* to generate the raw and\ninvariant features for training (*raw.txt* and *features.txt*).\n\nUse *data/tableto{lisp,svm}.pl* to convert the data set\nto a format which can be read by lisp or the support vector\nlibrary:\n```sh\n../tabletolisp.pl \u003c features.txt \u003e features.lisp\n```\nThe script *data/train2/scale.R* can be used to scale the\ndata appropriately.\n\n## How to train a neural network\nLoad *'learning-algorithm.lisp'* into lisp and execute\n\n```lisp\n(defparameter features\n  (make-instance 'learning-algorithm\n                 :network (make-instance 'ff-ann :topology (list :layers '(1023 15 10) :transf *tanh*))\n                 :data    (make-instance 'data :file \"features.lisp\" :percentage 10)\n                 :algorithm 'backprop-incremental))\n```\n\nto create a neural network with 1023x15x10 neurons, tanh activation\nfunction, where an incremental backprop algorithm is used. 10% of the\ndata set will be used as validation set.\n\nThen execute\n```lisp\n(run features #'(lambda (a) (\u003e= (epoch a) 200)) :learning-rate 0.001)\n```\nto train the network (the algorithm stops after 200 epochs).\n\nTo save/restore the weights of a network use:\n```lisp\n(save-weights    features \"features.weights\")\n(restore-weights features \"features.weights\")\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpbenner%2Flisp-backprop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpbenner%2Flisp-backprop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpbenner%2Flisp-backprop/lists"}