{"id":27247738,"url":"https://github.com/mbeardwell/language-guesser","last_synced_at":"2025-04-10T22:58:41.637Z","repository":{"id":203162038,"uuid":"159221175","full_name":"mbeardwell/language-guesser","owner":"mbeardwell","description":"Neural network built from scratch","archived":false,"fork":false,"pushed_at":"2025-03-03T00:42:27.000Z","size":13757,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-10T22:58:34.837Z","etag":null,"topics":[],"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/mbeardwell.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":"2018-11-26T19:24:33.000Z","updated_at":"2025-03-03T03:41:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"ae1fe899-97b8-4d3b-bbd5-2d993fc22aca","html_url":"https://github.com/mbeardwell/language-guesser","commit_stats":null,"previous_names":["abbyslab/language-guess-neural-net","mbeardwell/language-guess-neural-net"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mbeardwell%2Flanguage-guesser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mbeardwell%2Flanguage-guesser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mbeardwell%2Flanguage-guesser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mbeardwell%2Flanguage-guesser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mbeardwell","download_url":"https://codeload.github.com/mbeardwell/language-guesser/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248312147,"owners_count":21082638,"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":"2025-04-10T22:58:40.943Z","updated_at":"2025-04-10T22:58:41.615Z","avatar_url":"https://github.com/mbeardwell.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Language Recognition Using Neural Networks\n\nThis project implements a **feedforward neural network from scratch** to classify words into different languages **without using pre-built machine learning libraries**. It was developed as part of an Extended Project Qualification (EPQ) during A-levels in 2017, for which I received an A\\*.\n\nWhile originally an academic project, this implementation remains a pure, low-level demonstration of neural networks, covering forward propagation, backpropagation, weight optimisation, and training strategies—all coded manually without TensorFlow or PyTorch.\n\n## Project Paper\nFor a detailed explanation of the methodology, implementation, and results, read the full project paper [here](./docs/Neural_Network_Language_Classifier.pdf).\n\n## Results\n- Best accuracy: 69.3% (compared to 16.7% random baseline).\n- Languages tested: English, French, German, Latin, Italian, Greek.\n- Tuned network structures: 1-3 hidden layers, 40-200 neurons per layer.\n- Key findings: More hidden layers increased overfitting, while a 200-neuron, 1-hidden-layer model performed best.\n\n## Installation \u0026 Usage\n### Requirements\n- Python 3.0 or later\n- NumPy\n\n### Running the Program\n1. Install dependencies:\n```bash\npython3 -m pip install numpy\n```\n\n2. Clone the repository:\n```bash\ngit clone https://github.com/mbeardwell/language-guesser.git\ncd language-guesser\n```\n\n3.  Run the artefact:\n```bash\npython3 artefact.py\n```\n\nFurther Improvements\n-----------------------\n\n*   Increase training iterations to push accuracy beyond 70%.\n*   Experiment with different activation functions (e.g., ReLU).\n*   Incorporate additional languages to assess scalability.\n*   Explore convolutional networks (CNNs) to better capture word patterns.\n\n* * *\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmbeardwell%2Flanguage-guesser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmbeardwell%2Flanguage-guesser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmbeardwell%2Flanguage-guesser/lists"}