Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/thefcraft/thefcraft-ai-nn

Last synced: 7 days ago
JSON representation

Host: GitHub
URL: https://github.com/thefcraft/thefcraft-ai-nn
Owner: thefcraft
Created: 2024-05-28T07:43:19.000Z (6 months ago)
Default Branch: main
Last Pushed: 2024-05-28T09:17:27.000Z (6 months ago)
Last Synced: 2024-05-28T18:09:48.782Z (6 months ago)
Language: Jupyter Notebook
Size: 21.5 KB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # thefcraft-ai-nn

This is a basic example of how to make neural networks from scratch (you can replace numpy with c++ and cuda)

- in this code i use autograd/micrograd like implementation to track the gradients.

## DEMO

results.txt

```

EPOCH: 0 | LOSS: 0.1732

EPOCH: 100 | LOSS: 0.1672

EPOCH: 200 | LOSS: 0.1614

EPOCH: 300 | LOSS: 0.1561

EPOCH: 400 | LOSS: 0.1510

EPOCH: 500 | LOSS: 0.1463

EPOCH: 600 | LOSS: 0.1418

EPOCH: 700 | LOSS: 0.1376

EPOCH: 800 | LOSS: 0.1336

EPOCH: 900 | LOSS: 0.1299

EPOCH: 1000 | LOSS: 0.1263

EPOCH: 1100 | LOSS: 0.1229

EPOCH: 1200 | LOSS: 0.1197

EPOCH: 1300 | LOSS: 0.1167

EPOCH: 1400 | LOSS: 0.1138

EPOCH: 1500 | LOSS: 0.1111

EPOCH: 1600 | LOSS: 0.1085

EPOCH: 1700 | LOSS: 0.1060

EPOCH: 1800 | LOSS: 0.1037

EPOCH: 1900 | LOSS: 0.1014

EPOCH: 2000 | LOSS: 0.0993

EPOCH: 2100 | LOSS: 0.0972

EPOCH: 2200 | LOSS: 0.0952

EPOCH: 2300 | LOSS: 0.0933

EPOCH: 2400 | LOSS: 0.0915

EPOCH: 2500 | LOSS: 0.0898

EPOCH: 2600 | LOSS: 0.0881

EPOCH: 2700 | LOSS: 0.0865

EPOCH: 2800 | LOSS: 0.0849

EPOCH: 2900 | LOSS: 0.0834

EPOCH: 3000 | LOSS: 0.0820

EPOCH: 3100 | LOSS: 0.0806

EPOCH: 3200 | LOSS: 0.0792

EPOCH: 3300 | LOSS: 0.0779

EPOCH: 3400 | LOSS: 0.0767

EPOCH: 3500 | LOSS: 0.0755

EPOCH: 3600 | LOSS: 0.0743

EPOCH: 3700 | LOSS: 0.0732

EPOCH: 3800 | LOSS: 0.0721

EPOCH: 3900 | LOSS: 0.0710

EPOCH: 4000 | LOSS: 0.0699

EPOCH: 4100 | LOSS: 0.0689

EPOCH: 4200 | LOSS: 0.0680

EPOCH: 4300 | LOSS: 0.0670

EPOCH: 4400 | LOSS: 0.0661

EPOCH: 4500 | LOSS: 0.0652

EPOCH: 4600 | LOSS: 0.0643

EPOCH: 4700 | LOSS: 0.0635

EPOCH: 4800 | LOSS: 0.0626

EPOCH: 4900 | LOSS: 0.0618

Accuracy on test data: 0.9474

```