{"id":26932963,"url":"https://github.com/jkosla/neural_network_from_scratch_numpy","last_synced_at":"2026-04-10T16:44:00.420Z","repository":{"id":285371139,"uuid":"957889595","full_name":"jkosla/neural_network_from_scratch_numpy","owner":"jkosla","description":"Neural Network From Scratch in Python | Build a simple neural network from scratch using pure Python and NumPy. Learn about forward propagation, backpropagation, and training with gradient descent. Accompanies my Medium article.","archived":false,"fork":false,"pushed_at":"2025-03-31T10:25:56.000Z","size":420,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T11:23:37.695Z","etag":null,"topics":["ai","aritificial-intelligence","medium","nerual-networks","numpy","python3","tutorial"],"latest_commit_sha":null,"homepage":"https://medium.com/@jkosla/introduction-to-neural-networks-building-a-neural-network-from-scratch-in-python-with-d7b84b2b64b7","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/jkosla.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":"2025-03-31T10:01:36.000Z","updated_at":"2025-03-31T10:25:59.000Z","dependencies_parsed_at":"2025-03-31T11:23:39.104Z","dependency_job_id":"e1d57ab5-9945-4f75-9e1a-bc5d5489be3d","html_url":"https://github.com/jkosla/neural_network_from_scratch_numpy","commit_stats":null,"previous_names":["jkosla/neural_network_from_scratch_numpy"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkosla%2Fneural_network_from_scratch_numpy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkosla%2Fneural_network_from_scratch_numpy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkosla%2Fneural_network_from_scratch_numpy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkosla%2Fneural_network_from_scratch_numpy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jkosla","download_url":"https://codeload.github.com/jkosla/neural_network_from_scratch_numpy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246785489,"owners_count":20833498,"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":["ai","aritificial-intelligence","medium","nerual-networks","numpy","python3","tutorial"],"created_at":"2025-04-02T09:17:01.630Z","updated_at":"2026-04-10T16:44:00.385Z","avatar_url":"https://github.com/jkosla.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 Neural Network From Scratch in Python\n\nThis repository contains the full implementation of a **simple neural network built from scratch** in Python, as demonstrated in my [Medium article](\u003chttps://medium.com/@jkosla/introduction-to-neural-networks-building-a-neural-network-from-scratch-in-python-with-d7b84b2b64b7\u003e).\n\n---\n\n## 📖 Overview\n\nIn this project, we build a **fully connected neural network** from scratch without using deep learning libraries like PyTorch or TensorFlow. The implementation includes:\n\n- **Forward Propagation**\n- **Backpropagation**\n- **Training with Gradient Descent**\n- **Evaluation \u0026 Accuracy Calculation**\n\nThe code is designed to be simple and educational, demonstrating the core concepts of neural networks. Perfect for beginners who want to understand how neural networks work under the hood!\n\n---\n\n## 📂 Files\n\n- `simple_nn.py` — Implementation of the neural network.\n- `train.py` — Training script with evaluation functions.\n- `dataset.py` — Helper functions for data processing and evaluation.\n---\n\n## 💡 Getting Started\n\n### Requirements\n- Python 3.x\n- NumPy\n\nInstall dependencies:\n```bash\npip install numpy\npip install matplotlib\n```\n## Usage:\n\n```python\n%matplotlib inline\nfrom dataset import visualize_classification, XORDataset\nimport matplotlib.pyplot as plt\nfrom simple_nn import SimpleClassifier, GradientDescent\nfrom train_nn import train_model, eval_model, create_data_loader\n```\n\n\n```python\n\nnum_inputs = 2\nnum_hidden = 4\nnum_outputs = 1\n\ntrain_dataset = XORDataset(size=2500)\ntest_dataset = XORDataset(size=500)\n\ntrain_data_loader = create_data_loader(train_dataset)\ntest_data_loader = create_data_loader(test_dataset)\n\n\nmodel = SimpleClassifier(num_inputs, num_hidden, num_outputs)\noptimizer = GradientDescent(lr=0.01)\n```\n\n\n```python\n_ = visualize_classification(model, test_dataset.data, test_dataset.label)\n```\n\n\n    \n![png](output_2_0.png)\n    \n\n\n\n```python\ntrain_model(model, train_data_loader, optimizer)\neval_model(model, test_data_loader)\n_ = visualize_classification(model, test_dataset.data, test_dataset.label)\n```\n\n    Model Accuracy: 100.00%\n\n\n\n    \n![png](output_3_1.png)\n    \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjkosla%2Fneural_network_from_scratch_numpy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjkosla%2Fneural_network_from_scratch_numpy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjkosla%2Fneural_network_from_scratch_numpy/lists"}