{"id":20059044,"url":"https://github.com/shivang8/digit-recognition","last_synced_at":"2026-04-08T14:31:34.282Z","repository":{"id":124047729,"uuid":"115397758","full_name":"shivang8/Digit-Recognition","owner":"shivang8","description":"Digit Recognition using backpropagation algorithm on Artificial Neural Network with MATLAB. Dataset used from MNSIT.","archived":false,"fork":false,"pushed_at":"2018-02-12T09:45:01.000Z","size":18222,"stargazers_count":6,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-05-05T15:47:26.397Z","etag":null,"topics":["artificial-neural-networks","backpropagation-learning-algorithm","digit-recognition","matlab","mnsit"],"latest_commit_sha":null,"homepage":null,"language":"Matlab","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/shivang8.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,"zenodo":null}},"created_at":"2017-12-26T07:29:25.000Z","updated_at":"2018-11-29T11:11:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"04666cfe-30d1-4a49-bc76-e3d3f560998e","html_url":"https://github.com/shivang8/Digit-Recognition","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/shivang8/Digit-Recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivang8%2FDigit-Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivang8%2FDigit-Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivang8%2FDigit-Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivang8%2FDigit-Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shivang8","download_url":"https://codeload.github.com/shivang8/Digit-Recognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivang8%2FDigit-Recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31559712,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T14:31:17.711Z","status":"ssl_error","status_checked_at":"2026-04-08T14:31:17.202Z","response_time":54,"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":["artificial-neural-networks","backpropagation-learning-algorithm","digit-recognition","matlab","mnsit"],"created_at":"2024-11-13T13:05:48.739Z","updated_at":"2026-04-08T14:31:34.233Z","avatar_url":"https://github.com/shivang8.png","language":"Matlab","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Digit-Recognition\n\n## Objective: To Train a Neural Network with one Hidden Layer using Back-Propogation Algorithm Such that it is capable of recognition Handwritten Digits.  \n\nWe have used MNSIT Handwritten digit dataset `mnsit_all.mat` that contains 60K training and 10K testing examples of handwritten digits. Each example in the dataset is represented ny 784 features corroponding to (28 * 28) pixel values ([0,255]). The classes are 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 corresponding to each digit.\u003cbr/\u003e\n\n# Accuracy Achieved\n\n**Percentage of Total Accuracy = 97**\u003cbr/\u003e\nPercentage of Accuracy of 0 = 98.5714\u003cbr/\u003e\nPercentage of Accuracy of 1 = 98.6784\u003cbr/\u003e\nPercentage of Accuracy of 2 = 96.9961\u003cbr/\u003e\nPercentage of Accuracy of 3 = 96.9307\u003cbr/\u003e\nPercentage of Accuracy of 4 = 96.945\u003cbr/\u003e\nPercentage of Accuracy of 5 = 96.6368\u003cbr/\u003e\nPercentage of Accuracy of 6 = 96.7641\u003cbr/\u003e\nPercentage of Accuracy of 7 = 97.2763\u003cbr/\u003e\nPercentage of Accuracy of 8 = 95.0719\u003cbr/\u003e\nPercentage of Accuracy of 9 = 95.8375\u003cbr/\u003e\n\n# Module wise explanation\n\n**mnist_all.mat :** It is your dataset required for processing.\u003cbr/\u003e\n\n**data_epoc200.mat :** Preprocessed data uptill 200 epocs or 200 Iterations.\u003cbr/\u003e\n\n**Visualization.m :** Used for visualizing images.\u003cbr/\u003e \n\n**main.m :** Used for calling `initilazition.m`, running epocs i.e. training the neural network using `training.m` and for calculating the accuracy of the neural network using `Accuracy.m`\u003cbr/\u003e \n\n**initilization.m :** Used for loading `mnist_all.mat`, initilizing weights, bias and target and calculating the sizes of dataset\u003cbr/\u003e \n\n**training.m :** Used for training the neural network. For converting image to black and white `binary_convertor.m`is used and for training `processing.m` is used.\u003cbr/\u003e \n\n**binary_convertor.m :** Used to convert image to black and white or the binary format.\u003cbr/\u003e \n\n**processing.m :** Used for finding the feed forward and then back propogating the neural network. `sigm.m` is used to find the symbodial values of the input matrix.\u003cbr/\u003e \n\n**Accuracy.m :** Used to calculate the accuracy of the neural network. `prediction.m` is used to predict the digit.\u003cbr/\u003e \n\n**prediction.m :** It is used to feed forward the neural network and predict the digit.\u003cbr/\u003e\u003cbr/\u003e\u003cbr/\u003e\n \n**IF YOU ENCOUNTER ANY BUGS OR FOR ANY SUGGESTIONS REGARDING THE IMPROVEMENT OF THE DIGIT RECOGNIZER FEEL FREE TO CONTACT ME :**\n\nShivang Srivastava\t-\tshivang.8@geu.ac.in\u003cbr/\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivang8%2Fdigit-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshivang8%2Fdigit-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivang8%2Fdigit-recognition/lists"}