Skip to content

Latest commit

 

History

History
25 lines (18 loc) · 861 Bytes

README.md

File metadata and controls

25 lines (18 loc) · 861 Bytes

Genetic Neural Network Trainer

This project shows an example of training a Multilayer Perceptron network with genetic algorithms.

The project's directory structure:

  • data/ - various data used for testing
    • data/mnist/ - dataset for handwritten digit recognition
    • data/models/ - models saved after training
  • gui/ - graphical user interface implemented using QT
  • include/ - main directory with the implementation
    • include/gnnt/mlp/ - compile-time Multilayer Perceptron network
    • include/gnnt/training/ - genetic algorithm implementation
  • test/ - test cases for activation functions with the Catch2 framework

Screenshots

The Graphical User Interface

GUI

Example prediction for manually drawn digit

GUI

Example of training a network

GUI