{"id":25228262,"url":"https://github.com/asherk7/neural-network-from-scratch","last_synced_at":"2026-05-18T02:32:32.400Z","repository":{"id":293337076,"uuid":"975176996","full_name":"asherk7/neural-network-from-scratch","owner":"asherk7","description":"Creating a Convolutional Neural Network from scratch, modeled after ResNet","archived":false,"fork":false,"pushed_at":"2025-05-20T00:30:03.000Z","size":37,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-18T15:39:02.630Z","etag":null,"topics":["classification","cnn","ml","neural-network","numpy","python","resnet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/asherk7.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-04-29T22:57:30.000Z","updated_at":"2025-06-05T21:36:58.000Z","dependencies_parsed_at":"2025-08-18T15:27:48.291Z","dependency_job_id":null,"html_url":"https://github.com/asherk7/neural-network-from-scratch","commit_stats":null,"previous_names":["asherk7/neural-network-from-scratch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/asherk7/neural-network-from-scratch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fneural-network-from-scratch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fneural-network-from-scratch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fneural-network-from-scratch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fneural-network-from-scratch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/asherk7","download_url":"https://codeload.github.com/asherk7/neural-network-from-scratch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fneural-network-from-scratch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33162613,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-17T22:39:12.733Z","status":"online","status_checked_at":"2026-05-18T02:00:06.436Z","response_time":71,"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":["classification","cnn","ml","neural-network","numpy","python","resnet"],"created_at":"2025-02-11T09:52:21.897Z","updated_at":"2026-05-18T02:32:32.381Z","avatar_url":"https://github.com/asherk7.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Convolutional Neural Network (CNN) from Scratch  \nCreating a Convolutional Neural Network (CNN) from scratch using Python and NumPy, model is a simplified version of the ResNet architecture from the paper [\"Deep Residual Learning for Image Recognition\"](https://arxiv.org/abs/1512.03385).  \n\n## Overview  \nThis repository contains an implementation of a convolutional neural network and the popular components, built entirely from scratch using Python and NumPy, modeled after a simple ResNet. The goal of this project is to gain a deep understanding of the inner workings of neural networks, including:  \n- Forward propagation  \n- Backward propagation  \n- Activation functions  \n- Loss functions  \n- Optimization techniques\n- Residual connections\n\nThe network will be trained and evaluated on the **CIFAR-10 dataset**, a widely used benchmark for image classification tasks.  \n\n---\n\n## Features  \n- Manual implementation of key neural network components:\n  - Multiple layers \n  - Non-linear activation functions \n  - Loss functions\n  - Gradient descent and backpropagation\n  - Residual connections\n- Training and evaluation pipeline for the CIFAR-10 dataset\n\n---\n\n## Objectives  \n1. Understand the mathematical foundations of neural networks.  \n2. Implement a neural network without relying on high-level libraries like TensorFlow or PyTorch.  \n3. Build intuition on how different components work together.  \n\n---\n\n## Prerequisites  \n- **Python 3.8+**\n- **NumPy 2.2.1**\n- Basic knowledge of linear algebra, calculus (derivatives \u0026 multi-variable), and programming.  \n\n---\n\n## Installation  \n1. Clone this repository:  \n   ```bash\n   git clone https://github.com/asherk7/neural-network-from-scratch.git\n   cd neural-network-from-scratch\n   ```\n\n---\n\n## Usage\n1. Make sure you have the required libraries above.\n2. Download the CIFAR-10 dataset, rename it to `data`, and place it in the same directory as the script. The dataset can be downloaded from [here](https://www.cs.toronto.edu/~kriz/cifar.html).\n3. Run the cifar script to train the model:  \n   ```bash\n   python cifar.py\n   ```\n4. The model will be trained on the CIFAR-10 dataset, and you can monitor the training process through the printed metrics.\n5. After training, the model's performance will be evaluated on the test set, and results will be displayed.\n\n---\n\n## References\n- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)\n- [Build a Neural Network from scratch in C++ to deeply understand how it works, not just how to use it](https://medium.com/@sirawitchokphantavee/build-a-neural-network-from-scratch-in-c-to-deeply-understand-how-it-works-not-just-how-to-use-008426212f57)\n- [Neural Networks from Scratch in Python](https://www.youtube.com/playlist?list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3)\n- [CIFAR-10 Dataset](https://www.cs.toronto.edu/~kriz/cifar.html)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasherk7%2Fneural-network-from-scratch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fasherk7%2Fneural-network-from-scratch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasherk7%2Fneural-network-from-scratch/lists"}