jdoxey / neural-network-c

Simple neural network written in simple C

Simple Neural Network written in C

(LLVM on macOS, GCC on Linux, MSVC on Windows)

This is a very basic neural network implementation written with simple C.

I really just created this to learn more about the internals of neural networks. I'm making it public in case anyone else finds it helpful or useful.

Features

• Allows abitrary number of layers, and nodes in each layer (feed-forward only)
• Processes multiple training examples at a time
• Good unit test coverage
• Load and save weight values to file

Improvement Potential

• Include bias nodes
• Paralellisation across CPU and/or GPU to increase speed
• Choice of activation function at different layers

Usage

1. Create/allocate a new neural network with any number of layers, and any number of nodes in each layer, e.g.

   nn_Network *network = nn_Network_alloc("2, 3, 1");

2. Randomise weights within the network

   nn_Network_randomiseWeightsBetweenMinAndMax(network, -3.0, 3.0);

3. Set up training input and output data, e.g.

   nn_Matrix *trainingDataInputs = nn_Matrix_allocWithValues(4, 2,
   	0.0, 0.0,
   	0.0, 1.0,
   	1.0, 0.0,
   	1.0, 1.0
   );
   nn_Matrix *trainingDataOutputs = nn_Matrix_allocWithValues(4, 1,
   	1.0,
   	0.0,
   	0.0,
   	1.0
   );

4. Complete a training pass (forward, then backward pass with weight updates),

   double error = nn_Network_train(network, trainingDataInputs, trainingDataOutputs, 0.3);

   Complete this step until error is at an acceptable level.

5. Clean up memory,

   nn_Matrix_free(trainingDataInputs);
   nn_Matrix_free(trainingDataOutputs);
   nn_Network_free(network);

6. Link in the C math library when building, e.g.

   cc -o example example.c nn_Network.c nn_Matrix.c -lm