Skip to content

Latest commit

 

History

History
27 lines (23 loc) · 976 Bytes

README.md

File metadata and controls

27 lines (23 loc) · 976 Bytes

TSP NN Training

This repository is one of three parts that combines into one bigger project that resolves Travelling Salesman Problem using recurrent neural network.

Technologies

Used technologies:

  • Python 3.4
  • PyBrain

Usage

Make sure that you're using Python 3.4 and you've got PyBrain installed.
To train neural network run main.py script:

python3 -m main

Script will generate many neural networks (in networks subfolder) that have been saved in 30 seconds interval between training. To choose the best one use another script:

python3 -m testing

It will check average percentage difference between correct TSP solution and NN solution. The best network will be printed out at the end.

Other project repositories

Authors