{"id":20374277,"url":"https://github.com/snwfdhmp/neural-networks","last_synced_at":"2026-05-04T16:38:48.465Z","repository":{"id":98729368,"uuid":"77609891","full_name":"snwfdhmp/neural-networks","owner":"snwfdhmp","description":"Artificial neural networks that performs number recognition functions using FANN library","archived":false,"fork":false,"pushed_at":"2016-12-30T16:12:54.000Z","size":67,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-26T09:08:28.547Z","etag":null,"topics":["ai","ann","artificial-intelligence","artificial-neural-networks","fann","intelligence","neurons","weights-possibilities"],"latest_commit_sha":null,"homepage":"","language":"C++","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/snwfdhmp.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":"2016-12-29T12:13:49.000Z","updated_at":"2019-03-16T12:26:12.000Z","dependencies_parsed_at":"2023-06-25T23:44:10.894Z","dependency_job_id":null,"html_url":"https://github.com/snwfdhmp/neural-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/snwfdhmp%2Fneural-networks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snwfdhmp%2Fneural-networks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snwfdhmp%2Fneural-networks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snwfdhmp%2Fneural-networks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/snwfdhmp","download_url":"https://codeload.github.com/snwfdhmp/neural-networks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241921823,"owners_count":20042763,"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":["ai","ann","artificial-intelligence","artificial-neural-networks","fann","intelligence","neurons","weights-possibilities"],"created_at":"2024-11-15T01:23:25.833Z","updated_at":"2026-05-04T16:38:48.310Z","avatar_url":"https://github.com/snwfdhmp.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IA repository\n\nMy first tries with Artificial Intelligence.\n\nI'm actually using the FANN library to emulate Neural Networks.\n\nObservations :\n\n- The \"intelligence\" of a trained ANN (Artificial Neural Network) highly depends on the number of hidden neurons layers and their number of neurons. And more isn't necessarily better.\nFor a simple problem (a NOT) (with input 1, expected is 0, with input 0, expect is 1), a uniq layer with a uniq neuron is sufficient to get a very nice result (no errors on 200k tests), with 37 Epochs of training.\nBut with 50 layers of 5 neurons each, the ANN has still an error rate of 25% after 2000 Epochs of training.\nMaybe with a lot more training, this configuration will work, but we can do it simply with only 1 neuron, so ... ;)\n\n\u003ch2\u003e 1-2-2-1 configuration seems more efficient than 1-4-1 ... \u003c/h2\u003e\n\nWhat's the reason of that ? Let's try to figure it out.\n\n\n- How many \"synapse\" can we have on the first config ?\n\nfirst\n\n\tfirst[0]-\u003esecond[0]\n\tfirst[0]-\u003esecond[1]\n\nthen\n\n\tsecond[0]-\u003ethird[0]\n\tsecond[0]-\u003ethird[1]\n\tsecond[1]-\u003ethird[0]\n\tsecond[1]-\u003ethird[1]\n\nfinal\n\n\tthird[0]-\u003efirst[0]\n\tthird[1]-\u003efirst[0]\n\nSo we get a total amount of \u003cb\u003e2 + 4 + 2 = 8 synapses\u003c/b\u003e. (and so 8 different weights possibilities).\n\n- What about the second configuration ?\n\nfirst\n\n\tfirst[0]-\u003esecond[0]\n\tfirst[0]-\u003esecond[1]\n\tfirst[0]-\u003esecond[2]\n\tfirst[0]-\u003esecond[3]\n\nfinal\n\n\tsecond[0]-\u003ethird[0]\n\tsecond[1]-\u003ethird[0]\n\tsecond[2]-\u003ethird[0]\n\tsecond[3]-\u003ethird[0]\n\nSo we get a total of \u003cb\u003e4 + 4 = 8 synapses\u003c/b\u003e. (still 8 different weights possibilities).\n\nThe numbers of activation functions is still the same in both : 4.\n\n\u003ch3\u003eHow can we get a significative difference of capability ?\u003c/h3\u003e\n\nGood question.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnwfdhmp%2Fneural-networks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsnwfdhmp%2Fneural-networks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnwfdhmp%2Fneural-networks/lists"}