{"id":23892492,"url":"https://github.com/anshumansinha3301/neural-network","last_synced_at":"2026-05-16T15:34:31.114Z","repository":{"id":270844368,"uuid":"911630179","full_name":"anshumansinha3301/Neural-Network","owner":"anshumansinha3301","description":"MNIST Using Neural Network project from scratch in jupyter notebook with basic python concepts (Using Numpy and Matplotlib)","archived":false,"fork":false,"pushed_at":"2025-01-03T15:43:31.000Z","size":120,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-23T05:43:17.049Z","etag":null,"topics":["anshumansinha3301","bitfusiondynamics","matplotlib-python","mnist-handwriting-recognition","neural-networks","numpy","open-source","python"],"latest_commit_sha":null,"homepage":"","language":null,"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/anshumansinha3301.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":"2025-01-03T13:23:55.000Z","updated_at":"2025-01-08T17:54:31.000Z","dependencies_parsed_at":"2025-01-03T14:36:07.189Z","dependency_job_id":"c4f870bf-9f26-426f-b636-23b2afb34a90","html_url":"https://github.com/anshumansinha3301/Neural-Network","commit_stats":null,"previous_names":["anshumansinha3301/neural-network"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/anshumansinha3301/Neural-Network","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anshumansinha3301%2FNeural-Network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anshumansinha3301%2FNeural-Network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anshumansinha3301%2FNeural-Network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anshumansinha3301%2FNeural-Network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anshumansinha3301","download_url":"https://codeload.github.com/anshumansinha3301/Neural-Network/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anshumansinha3301%2FNeural-Network/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33108190,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"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":["anshumansinha3301","bitfusiondynamics","matplotlib-python","mnist-handwriting-recognition","neural-networks","numpy","open-source","python"],"created_at":"2025-01-04T13:55:30.675Z","updated_at":"2026-05-16T15:34:31.073Z","avatar_url":"https://github.com/anshumansinha3301.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural-Network\nThis project is a Python-based implementation of a neural network built from scratch to classify handwritten digits,\nlikely using the MNIST dataset. It begins by loading the dataset and preprocessing it, which includes normalizing \npixel values by scaling them between 0 and 1. The dataset is split into training and development sets to evaluate the model's performance.\n\nThe neural network architecture consists of two layers. The first is a hidden layer that uses the \nReLU (Rectified Linear Unit) activation function to introduce non-linearity. The second is an output layer that \napplies the softmax activation function to generate probabilities for multi-class classification.\n\nThe project includes forward propagation, where the inputs are passed through the layers, and the output is computed.\nIt also handles one-hot encoding for the target labels and uses basic optimization techniques to update model parameters.\nThe model's performance is evaluated on both the training and development datasets, showcasing an end-to-end approach \nto building a neural network from scratch.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanshumansinha3301%2Fneural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanshumansinha3301%2Fneural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanshumansinha3301%2Fneural-network/lists"}