emilwallner/Deep-Learning-From-Scratch

Six snippets of code that made deep learning what it is today.

48
/ 100
Emerging

This resource provides foundational code examples to understand how deep learning algorithms work from the ground up. It takes mathematical concepts like cost functions and gradient descent, and translates them into simple, executable code snippets. This is ideal for students, educators, or researchers who want to grasp the core mechanics behind deep neural networks.

263 stars. No commits in the last 6 months.

Use this if you want to understand the fundamental mathematical and algorithmic building blocks of deep learning by seeing and running simple, historical code examples.

Not ideal if you are looking for production-ready deep learning frameworks or tools to apply to complex real-world datasets.

machine-learning-education algorithm-fundamentals neural-network-basics computational-mathematics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

263

Forks

57

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 10, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/emilwallner/Deep-Learning-From-Scratch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.