{"id":25986988,"url":"https://github.com/belhoussine/neuralnet","last_synced_at":"2026-04-20T07:31:12.746Z","repository":{"id":172555995,"uuid":"295027749","full_name":"Belhoussine/NeuralNet","owner":"Belhoussine","description":"A Machine Learning library for Neural Networks fully written in python. It supports multiple layers of neurons and offers a variety of activation functions, optimization algorithms, and utility functions.","archived":false,"fork":false,"pushed_at":"2022-04-27T19:26:53.000Z","size":11258,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-12-09T22:20:22.438Z","etag":null,"topics":["artifical-neural-network","library","machine-learning","neural-network","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Belhoussine.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":"2020-09-12T21:17:56.000Z","updated_at":"2022-04-27T19:26:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"9f1e074b-3b63-4b25-ac42-6b8ec2182d1f","html_url":"https://github.com/Belhoussine/NeuralNet","commit_stats":null,"previous_names":["belhoussine/neuralnet"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Belhoussine/NeuralNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Belhoussine%2FNeuralNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Belhoussine%2FNeuralNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Belhoussine%2FNeuralNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Belhoussine%2FNeuralNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Belhoussine","download_url":"https://codeload.github.com/Belhoussine/NeuralNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Belhoussine%2FNeuralNet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32037805,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-20T00:18:06.643Z","status":"online","status_checked_at":"2026-04-20T02:00:06.527Z","response_time":94,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["artifical-neural-network","library","machine-learning","neural-network","python"],"created_at":"2025-03-05T12:47:25.548Z","updated_at":"2026-04-20T07:31:12.722Z","avatar_url":"https://github.com/Belhoussine.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Machine Learning Library\n## Usage Notes:\nPython3 is needed to use this library.\n```\ngit clone https://github.com/Belhoussine/NeuralNet\ncd NeuralNet\npip3 install requirements.txt\n```\n\n## Neural Network Specifications\n\n### 1. Artificial Neural Network:\n- [x] Supports multiple layers\n- [x] Supports multiple neurons per layer\n- [ ] Train:\n    - [x] Forward Propagation\n    - [ ] Back Propagation  \n    - [x] Run in Epochs\n    - [x] Supports mini batches\n- [x] Predict\n- [x] Verbose training phase \n\n### 2. Activation Functions:\n\n- [x] Sigmoid (Non linear mapping between 0 and 1)\n- [x] Softmax (Non Linear Probability Distribution)\n- [x] ReLU (Rectified Linear Unit)\n- [x] Leaky ReLU (Leaking ReLU on negative values)\n- [x] TanH (Hyperbolic Tangent)\n- [x] ELU (Exponential Linear Unit)\n\n### 3. Loss Functions:\n\n- [x] RMSE (Root Mean Squared Error)\n- [x] MSE (Mean Squared Error)\n- [x] SSE (Sum Squared Error)\n- [x] MAE (Mean Absolute Error)\n- [x] LogCosH (Log of Hyperbolic cosine)\n- [x] Huber (Hyperbolic Tangent)\n- [ ] Cross Entropy (Logistic Loss)\n- [ ] Least Squares \n\n### 3. Optimization Algorithms:\n\n- [ ] Batch Gradient Descent\n- [ ] SGD (Stochastic Gradient Descent)\n- [ ] Mini-Batch Gradient Descent\n- [ ] General Purpose Gradient Descent\n- [ ] ADAM (Adaptive Moment Estimation)\n- [ ] RMSProp\n\n### 4. Utility Functions:\n\n- [x] Download MNIST dataset from remote server\n- [x] Flatten (Convert 2D Matrix to vector)\n- [x] One Hot Encoding (Convert numerical to categorical)\n- [x] One Hot Decoding (Convert categorical to numerical)\n- [x] Normalization Function (Linear Mapping between 0 and 1)\n- [x] Accurary function (Compute Model Accuracy)\n- [x] Activate (Applies given activation function)\n- [x] Compute Loss (with chosen loss function)\n- [ ] Optimize (Applies given optimizer on model)\n- [x] Shuffle (Shuffles training data)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbelhoussine%2Fneuralnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbelhoussine%2Fneuralnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbelhoussine%2Fneuralnet/lists"}