{"id":18314357,"url":"https://github.com/pc9795/mlp","last_synced_at":"2025-10-12T23:10:59.926Z","repository":{"id":121080547,"uuid":"262469164","full_name":"pc9795/mlp","owner":"pc9795","description":"A multi-layer perceptron (A.K.A neural network :bow:) from scratch in Java :coffee:.","archived":false,"fork":false,"pushed_at":"2020-06-16T18:56:36.000Z","size":651,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-02-15T06:41:28.175Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Java","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/pc9795.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":"2020-05-09T02:09:46.000Z","updated_at":"2020-06-17T12:46:48.000Z","dependencies_parsed_at":null,"dependency_job_id":"a92a123b-e6f6-4383-b4a5-aa0783592f0e","html_url":"https://github.com/pc9795/mlp","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/pc9795%2Fmlp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pc9795%2Fmlp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pc9795%2Fmlp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pc9795%2Fmlp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pc9795","download_url":"https://codeload.github.com/pc9795/mlp/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248045220,"owners_count":21038552,"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":[],"created_at":"2024-11-05T16:32:17.316Z","updated_at":"2025-10-12T23:10:59.842Z","avatar_url":"https://github.com/pc9795.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"Import this project as a maven project in your preferred IDE\n* **Intellij** - https://www.lagomframework.com/documentation/1.6.x/java/IntellijMaven.html\n* **Eclipse** - https://vaadin.com/learn/tutorials/import-maven-project-eclipse\n\n### Project Structure\n\n* `experiments` - All the code for the experiments ran. XOR, Sin and Letter recognition\n* `experiments.utils` - Utility methods which are used in evaluating the experiments\n* `mlp` - All the code for Multi layer perceptron implementation\n* `mlp.activations` - All the activation functions which can be used - RELU, Leaky RELU, Sigmoid, Linear, Tanh, Softmax\n* `mlp.exceptions` - Custom exceptions for this project\n* `mlp.loss_functions` - All the loss function which can be used - Squared loss, Cross entropy, Binary cross entropy\n\nSample Training and testing Example\n```\n    int ni = ...\n    int nh = ...\n    int no = ...\n    int randomState = ...\n    double learningRate = ...\n    int epochs = ...\n    ActivationType type = ...\n    boolean isClassification = ...\n    boolean isMulticlass = ...\n    int batchSize = ...\n    \n    //Create an multi layer perceptron object\n    MultilayerPerceptron mlp = new MultilayerPerceptron(ni, nh, no, randomState, learningRate, epochs, type, \n        isClassification, isMulticlass, bathcSize);\n\n    //Training the MLP\n    mlp.fit(input, output);\n\n    //Get the predictions of the MLP\n    double predicted[][] = mlp.predict(input);\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpc9795%2Fmlp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpc9795%2Fmlp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpc9795%2Fmlp/lists"}