A minimal autograd engine
Project description
mikegrad
This repository is an implementation of Andrej Karpathy's "Neural Networks: Zero to Hero - Micrograd" video. The project implements backpropagation from scratch.
Features
- Autograd engine for automatic differentiation
- Backpropagation implementation
- Basic neural network components
- Sigmoid activation function
- Example training with toy regression data
TODO
- Refactor the codebase
- Publish to PyPI
- More activation functions
- More loss functions
- Support common optimizers (SGD, Adam)
- Add more examples
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mikegrad-0.1.0.tar.gz
(3.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mikegrad-0.1.0.tar.gz.
File metadata
- Download URL: mikegrad-0.1.0.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bea878969d6f44c08c8759d5db6e43529b3962442bbd8d5bf376ae2cdea88358
|
|
| MD5 |
bcb95f01b2f9b4a7c4a4b5b616d616d1
|
|
| BLAKE2b-256 |
4792169b137ce939d612cc4844e91d1e13e275d4aff54c2dc40a4a92d359fa67
|
File details
Details for the file mikegrad-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mikegrad-0.1.0-py3-none-any.whl
- Upload date:
- Size: 4.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e63baed437b70a4dea0d6313553fd5dbd8360dc0dd3bda61bf74c5ce5b67aae6
|
|
| MD5 |
48e32aa87625d96c05911b129b3e38ce
|
|
| BLAKE2b-256 |
9983ad9c07619d1c2e1bd4ca87b807b291cf4791033c91a6c49348580fad3c80
|
