A small Neural Network
Project description
Neural Network
A small Neural Network - Multilayer Perceptron made to learn how it works.
Warning : This is not a project for production use. I'm using this project to try to publish clean code, it's part of my learning how to manage a project, make R&D, and more.
Using Numba
I'm learning and using the library Numba to make this project. I have multiple goal :
- Make the project in normal python, without using the Numba lib, that's the pure learning part of how to make a Neural Network
- Make the project with Numba and use JiT to have better performance with the CPU
- Make the project with Numba and use CUDA to improve performance again
Genetic algorithm
I use genetic algorithm (in a very simple way i think, i'm not a mathematician xD) to make the learning part of the Neural Network. Back Propagation is on the way too.
Project details
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
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 morpyneural-0.0.2.tar.gz.
File metadata
- Download URL: morpyneural-0.0.2.tar.gz
- Upload date:
- Size: 7.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.9.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e5b606df01dab30f200a6d38b2b241f1fb60059434fd81cd247db0aefa9f9fc5
|
|
| MD5 |
36c3fd472910ebdb479554fe1dd0c98c
|
|
| BLAKE2b-256 |
102d28351c111e3ef469f4bd2ff3182377c0c2965f1f733a49a12909be89283a
|
File details
Details for the file morpyneural-0.0.2-py3-none-any.whl.
File metadata
- Download URL: morpyneural-0.0.2-py3-none-any.whl
- Upload date:
- Size: 11.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.9.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5b0a95292b3a9670af12085cb09ed3c8cf4bdd7eb106e059ed4bbcf4660c93e1
|
|
| MD5 |
3db1c549ccc204927bf6c4ee9febff86
|
|
| BLAKE2b-256 |
8b78f6b47c1901e91cad9930c0e385b94218556a8522b1f6f5a05388f47500c5
|