Nunn implements an artificial intelligent framework written in modern C++11, which supports artificial networks able to learn by example and other machine learning algorithms.
The project includes demo applications, which are an excellent prototype problem for neural networks learning:
- mnist_test application lets you evaluate multiple net configurations on MNIST
- ocr_test provides a GUI to write digits that can recognize by using MNIST trained nets
- TicTacToe game
- Xor-function implementation
- And-perceptron sample
- Hopfield test
Binaries for Windows have been built by using Microsoft Visual C++ 2015, so you may need to install Visual C++ Redistributable Packages.
To do this, search for "Visual C++ Redistributable Packages for Visual Studio 2015" or use the link
- Free open source neural network library
- Implements perceptron, MLP, RMLP and Hopfield NNs
- Implement Q-Learning algorithm
- Supports fully connected networks
- Back-propagation with MSE and Cross Entropy cost functions support
- Easy to use and understand
- Easy to save and load entire ANNs
- Includes non-trivial samples for Windows and Linux
- Samples include MNIST OCR Demo and TicTacToe
- Multi-platform, multi-architecture
- Exports neural network diagrams that you can draw using Graphviz dot
Be the first to post a review of nunn!