{"id":20027660,"url":"https://github.com/fabriziomusacchio/ann_with_numpy","last_synced_at":"2026-05-08T23:02:14.962Z","repository":{"id":224423580,"uuid":"763216039","full_name":"FabrizioMusacchio/ann_with_numpy","owner":"FabrizioMusacchio","description":"A how-to for building an artificial neural network from scratch using NumPy","archived":false,"fork":false,"pushed_at":"2024-02-25T21:09:34.000Z","size":198,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-12T17:25:00.926Z","etag":null,"topics":["ann","artificial-neural-networks","neural-network","numpy"],"latest_commit_sha":null,"homepage":"https://www.fabriziomusacchio.com/blog/2024-02-25-ann_from_scratch_using_numpy/","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/FabrizioMusacchio.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}},"created_at":"2024-02-25T21:02:13.000Z","updated_at":"2024-02-25T21:08:50.000Z","dependencies_parsed_at":"2024-02-25T22:23:39.772Z","dependency_job_id":"9cb1f8d1-350e-425e-8e30-f022bab3c396","html_url":"https://github.com/FabrizioMusacchio/ann_with_numpy","commit_stats":null,"previous_names":["fabriziomusacchio/ann_with_numpy"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FabrizioMusacchio%2Fann_with_numpy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FabrizioMusacchio%2Fann_with_numpy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FabrizioMusacchio%2Fann_with_numpy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FabrizioMusacchio%2Fann_with_numpy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FabrizioMusacchio","download_url":"https://codeload.github.com/FabrizioMusacchio/ann_with_numpy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241460046,"owners_count":19966516,"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":["ann","artificial-neural-networks","neural-network","numpy"],"created_at":"2024-11-13T09:11:17.150Z","updated_at":"2026-05-08T23:02:14.860Z","avatar_url":"https://github.com/FabrizioMusacchio.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Building a neural network from scratch using NumPy\n\nEver thought about building you own neural network from scratch by simply using NumPy? In this code example, we will do exactly that. We will build a simple feedforward neural network and train it on the MNIST dataset. The [MNIST dataset](https://en.wikipedia.org/wiki/MNIST_database) is a collection of 28x28 pixel grayscale images of handwritten digits (0-9). It is a popular dataset for getting started with machine learning and computer vision. The dataset contains 60,000 training images and 10,000 test images. The goal is to train a model that can correctly classify the images into their respective digit classes.\n\nThe entire tutorial can be found in this [blog post](https://www.fabriziomusacchio.com/blog/2024-02-25-ann_from_scratch_using_numpy/).\n\nFor reproducibility:\n\n```bash\nconda create -n numpy_ann python=3.11\nconda activate numpy_ann\nconda install -y mamba\nmamba install -y numpy matplotlib keras ipykernel\n```\n\nIf you want to run the code on an Apple Silicon chip, follow [these instructions](https://www.fabriziomusacchio.com/blog/2022-11-10-apple_silicon_and_tensorflow/) to install TensorFlow (required by Keras).\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffabriziomusacchio%2Fann_with_numpy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffabriziomusacchio%2Fann_with_numpy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffabriziomusacchio%2Fann_with_numpy/lists"}