Skip to content

Latest commit

 

History

History
15 lines (11 loc) · 692 Bytes

README.md

File metadata and controls

15 lines (11 loc) · 692 Bytes

This repository contains code for recognizing digits using Neural Networks. It is developed as part of the competition Digit Recognizer hosted by Kaggle. Check out this link for more details : https://www.kaggle.com/c/digit-recognizer

Visualization

The file digit_recognizer.py suppports plot for accuracies. Other additions should be straight-forward

Results

The output folder contains the results of running the network. The best accuracy of 0.99829 was achieved using Convolutional Networks with Rectified Linear Units.

Dependencies

This code is written in python. To use it you will need:

  • Python 2.7
  • Theano 0.7
  • A recent version of NumPy and matlplotlib