Frostday / Neural-Network-From-Scratch

Multiple types of neural networks hardcoded in Python from scratch without using any framework to understand their fundamental functioning.

Repository from Github https://github.comFrostday/Neural-Network-From-ScratchRepository from Github https://github.comFrostday/Neural-Network-From-Scratch

Neural Network From Scratch

Multiple types of neural networks hardcoded in Python from scratch without using any framework to understand their fundamental functioning.

Artificial Neural Network

Reference - https://towardsdatascience.com/neural-networks-from-scratch-easy-vs-hard-b26ddc2e89c7

  • The dataset used is the sklearn digits datasets which consists of 1797 number images of resolution 8x8.

  • The Neural Network model used can be seen below.

  • Results

After 1000 epochs

Loss Train Accuracy Test Accuracy
0.00213 99.87 98.33

Coming soon

  • CNNs

About

Multiple types of neural networks hardcoded in Python from scratch without using any framework to understand their fundamental functioning.

License:MIT License


Languages

Language:Python 100.0%