Skip to content

Latest commit

 

History

History
6 lines (4 loc) · 448 Bytes

README.md

File metadata and controls

6 lines (4 loc) · 448 Bytes

Science-Fair

This project creates a convolutional neural network, drawing inspiration from the sturcture of VGG-19.

Ideally, it will trian itself on a dataset of handwritten letters normally, and then be trained on top of that with an abnormally high training rate on letters that are written by a small number of people in order to overfit their data.

By doing this, it will be able to identify a piece of text as being written by one of them.