{"id":51570370,"url":"https://github.com/matthew-pisano/nuralpy","last_synced_at":"2026-07-10T19:01:46.873Z","repository":{"id":181095998,"uuid":"466880085","full_name":"matthew-pisano/NuralPy","owner":"matthew-pisano","description":"A python research project to analyze the differences between backpropagation, a genetic algorithm method, and the decision tree optimization on the training and execution of a neural network.","archived":false,"fork":false,"pushed_at":"2023-10-30T15:16:42.000Z","size":2067,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2023-10-30T16:27:56.616Z","etag":null,"topics":["artificial-neural-networks","numpy","python","research-project"],"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/matthew-pisano.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}},"created_at":"2022-03-06T23:13:26.000Z","updated_at":"2023-02-20T03:20:42.000Z","dependencies_parsed_at":"2023-07-14T02:42:43.684Z","dependency_job_id":null,"html_url":"https://github.com/matthew-pisano/NuralPy","commit_stats":null,"previous_names":["matthew-pisano/nuralpy"],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/matthew-pisano/NuralPy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthew-pisano%2FNuralPy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthew-pisano%2FNuralPy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthew-pisano%2FNuralPy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthew-pisano%2FNuralPy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/matthew-pisano","download_url":"https://codeload.github.com/matthew-pisano/NuralPy/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthew-pisano%2FNuralPy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35339931,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-10T02:00:06.465Z","response_time":60,"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":["artificial-neural-networks","numpy","python","research-project"],"created_at":"2026-07-10T19:01:45.792Z","updated_at":"2026-07-10T19:01:46.864Z","avatar_url":"https://github.com/matthew-pisano.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NeuralPy\n\nA python research project to analyze the differences between backpropagation, a genetic algorithm method, and the decision tree optimization on the training and execution of a neural network.\n\n## Aims and Objectives\n\nThe objective of the project is to compare the methods of backpropagation,\ngenetic algorithms, and decision trees on their abilities to predict a positive\ndiabetes diagnosis. For this project, we based our results on a training set\nfrom the Vanderbilt University Department of Biostatistics.\n\n## Implementation\n\nThe first steps to conducting the experiment were to craft each of the different\nneural networks. The implementation of each network was conducted in\nPython with extensive use of the *NumPy* library for its light and\nefficient array and matrix implementations.\n\n## Training and Testing\n\nFor training, each one of the three networks was given the same 80% proportion of the original data set and trained for 150 epochs and three independent trials. The loss function for each network is given by the sum of squared errors for every sample.\n\nEach trial was given a score for comparison. The score is given by the percent of correctly identified diagnoses divided by the time it took for the trial to complete. The higher the score, the better the performance of the algorithm.\n\n---\n\n## Execution\n\n**Requirements**:\n\n- Python 3.8 or higher\n- NumPy\n- MatPlotLib\n- Cv2\n\nRunning the main project file is as simple as:\n\n\u003e `python main.py`\n\nwhen in the src directory of the project.\nBy default, this will run the project in the exact configuration that was used in the presentation slides.\n\nModifying any of the parameters in the dictionaries in the main method will result in different execution behavior.  After each successful execution, the program will output the results of the testing, such as which guesses were correct or incorrect.\nThe program will also display a plot showing the loss and accuracy over time.\n\nThe `DecisionTree.py` file contains the logic for the decision tree.  Actually running the decision tree is not utilized in the main project, so this can be tested in the main method here.  Through this file, the decision tree can be run and tested for its accuracy.\n\nThe `TreeNeuralNet.py` and `Neuron.py` files are deprecated.  They are not utilized anywhere in the program and only exist for showing how the project has evolved.\nTheir run configurations were replaced early on in the project.  The active utilization of this section of code can be accessed from early commits from the github repository.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatthew-pisano%2Fnuralpy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatthew-pisano%2Fnuralpy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatthew-pisano%2Fnuralpy/lists"}