{"id":23388969,"url":"https://github.com/laserkelvin/learning-neural-networks","last_synced_at":"2025-10-08T21:41:22.771Z","repository":{"id":50142283,"uuid":"251671919","full_name":"laserkelvin/learning-neural-networks","owner":"laserkelvin","description":"A repository of notebooks for teaching neural networks","archived":false,"fork":false,"pushed_at":"2021-06-02T18:07:29.000Z","size":1194,"stargazers_count":6,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T07:05:32.076Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/laserkelvin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-03-31T16:58:48.000Z","updated_at":"2024-07-16T08:02:25.000Z","dependencies_parsed_at":"2022-08-25T16:12:30.618Z","dependency_job_id":null,"html_url":"https://github.com/laserkelvin/learning-neural-networks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/laserkelvin/learning-neural-networks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/laserkelvin%2Flearning-neural-networks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/laserkelvin%2Flearning-neural-networks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/laserkelvin%2Flearning-neural-networks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/laserkelvin%2Flearning-neural-networks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/laserkelvin","download_url":"https://codeload.github.com/laserkelvin/learning-neural-networks/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/laserkelvin%2Flearning-neural-networks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000706,"owners_count":26082837,"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","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"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":[],"created_at":"2024-12-22T02:35:45.708Z","updated_at":"2025-10-08T21:41:22.752Z","avatar_url":"https://github.com/laserkelvin.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Learning Neural Networks\n\n![splash](splash.png)\n\nThis repository contains a series of notebooks that demonstrate fundamentals of deep learning\nwith varying degrees of abstraction. The idea is that each notebook covers a part of deep learning\nnot necessarily with specific purposes in mind, but to try and get the core theoretical concepts\nwithout applying it to the usual problems like cat and handwriting classification.\n\n## How to use these notebooks\n\n[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/laserkelvin/learning-neural-networks/master)\n\nFor viewing and easy playing, the Binder button above will launch a Binder\nimage to try stuff out. I recommend opening this github repository in Google\nColab—we get free computational power in the form of free GPUs, why not use it?\nYou can get start up the notebooks [by navigating to this\nlink](https://colab.research.google.com/github/laserkelvin/learning-neural-networks).\n\nIf you'd like to make modifications and really play around with the notebooks\nhowever, I suggest you clone this repo and install the packages specified in\n`requirements.txt`.\n\nIn terms of the natural progression of things, this is the general gist/summary\nof each notebook:\n\n1. Fundamentals\n  - Dive into _why_ we should use neural networks and deep learning \n  - Low-level implementation of the core mechanics of neural networks, the perceptron, using NumPy\n  - Effect of non-linearities on our model output Teaching a neural network\n  - How neural networks learn; cost and autograd with Jax\n\n2. Primer On Auxiliary Functions\n  - Activation Functions\n  - Loss Functions\n  - Optimizers\n\n3. PyTorch Abstraction\n  - Good practices in PyTorch\n  - GPU Models\n\n## Acknowledgements\n\nI created these notebooks while doing the\n[deeplearning.ai](https://www.coursera.org/specializations/deep-learning)\nspecialization for deep learning. Andrew Ng and his team has put together a set\nof great courses, and so some of the things I'm describing in my notebooks are\ninspired (but not lifted!) from his videos.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flaserkelvin%2Flearning-neural-networks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flaserkelvin%2Flearning-neural-networks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flaserkelvin%2Flearning-neural-networks/lists"}