{"id":28363876,"url":"https://github.com/aryehky/ml-theory-to-implementation","last_synced_at":"2025-06-23T21:31:30.133Z","repository":{"id":295132349,"uuid":"989164862","full_name":"aryehky/ml-theory-to-implementation","owner":"aryehky","description":"📚🧠 Explores core machine learning concepts through interactive, hands-on Jupyter notebooks. From building a neural network from scratch to applying dimensionality reduction and classification with real-world libraries, this project bridges the gap between theory and practical application.","archived":false,"fork":false,"pushed_at":"2025-05-23T19:25:57.000Z","size":355,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-04T22:31:39.763Z","etag":null,"topics":["4d-database","jupyter-notebook","machine-learning","matploblib","numpy","pca-analysis"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/aryehky.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":"2025-05-23T16:56:28.000Z","updated_at":"2025-05-23T19:26:33.000Z","dependencies_parsed_at":"2025-05-23T20:28:21.786Z","dependency_job_id":"91433776-832d-4aeb-911a-fefcf1f585b1","html_url":"https://github.com/aryehky/ml-theory-to-implementation","commit_stats":null,"previous_names":["aryehky/ml-theory-to-implementation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/aryehky/ml-theory-to-implementation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryehky%2Fml-theory-to-implementation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryehky%2Fml-theory-to-implementation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryehky%2Fml-theory-to-implementation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryehky%2Fml-theory-to-implementation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aryehky","download_url":"https://codeload.github.com/aryehky/ml-theory-to-implementation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryehky%2Fml-theory-to-implementation/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261558807,"owners_count":23177095,"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":["4d-database","jupyter-notebook","machine-learning","matploblib","numpy","pca-analysis"],"created_at":"2025-05-28T19:39:49.973Z","updated_at":"2025-06-23T21:31:30.124Z","avatar_url":"https://github.com/aryehky.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 ML Foundations: Theory to Practice\n\nThis repository explores core machine learning concepts through interactive, hands-on Jupyter notebooks. From building a neural network from scratch to applying dimensionality reduction and classification with real-world libraries, this project bridges the gap between theory and practical application.\n\n---\n\n## 📚 Notebooks Overview\n\n| Notebook                         | Focus                          | Description                                                                                                                                         |\n| -------------------------------- | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `01_pca_dimensionality.ipynb`    | 📉 Dimensionality Reduction    | Uses Principal Component Analysis (PCA) to reduce high-dimensional data while preserving variance. Ideal for feature compression and visualization. |\n| `02_neural_net_numpy.ipynb`      | 🤖 Neural Network from Scratch | Implements a simple feedforward neural network using only NumPy. Covers forward propagation, backpropagation, and a training loop.                  |\n| `03_classification_models.ipynb` | 🧪 ML Classification           | Applies supervised learning techniques using scikit-learn. Includes data preprocessing, model training, evaluation, and comparison.                 |\n\n---\n\n## 🔍 Key Takeaways\n\n### 🎯 PCA\n\n* Reduced a 4D dataset to 2D while retaining \\~95% of variance.\n* Visualized separability of classes in reduced space.\n\n### 🛠️ Custom Neural Network\n\n* Built from scratch using NumPy (no ML frameworks).\n* Trained a neural net using manual backpropagation and gradient descent.\n* Demonstrated convergence on a synthetic dataset.\n\n### 📈 Classification Pipeline\n\n* Achieved \\~97% accuracy using logistic regression.\n* Visualized results via a confusion matrix.\n* Compared multiple models including SVM and Decision Trees.\n\n---\n\n## 🧰 Tech Stack\n\n* **Python** – Core scripting language\n* **NumPy** – Neural network implementation\n* **Scikit-learn** – PCA, classification, evaluation tools\n* **Matplotlib \u0026 Seaborn** – Visualization\n* **Jupyter Notebooks** – Interactive development\n\n---\n\n## 📁 Directory Structure\n\n```\nml-theory-to-practice/\n├── 01_pca_dimensionality.ipynb        # Dimensionality Reduction with PCA\n├── 02_neural_net_numpy.ipynb          # Neural Network built from scratch\n├── 03_classification_models.ipynb     # Supervised ML classification models\n└── README.md\n```\n\n---\n\n## 🚀 Project Goals\n\n* Solidify foundational machine learning theory through hands-on implementation\n* Develop intuition for model behavior, training dynamics, and evaluation\n* Showcase practical skills for portfolio use or collaborative work\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faryehky%2Fml-theory-to-implementation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faryehky%2Fml-theory-to-implementation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faryehky%2Fml-theory-to-implementation/lists"}