This is a small pure C header-only, zero-dependency library for arbitrarily deep neural networks. It is my first attempt to write a scientific project in C but the speed is already outstanding. I made this library in order to assist me with my doctoral research.
It is CPU only (soon with support for cuBLAS and cuDNN if I get my hands on an NVIDIA GPU). I have plans to extend it for CNNs.
- Python: python-libartificial
- R: soon
The procedure does not have a hardcoded depth (it can have as many layers with as many nodes as you want-beware of your heap limits).
The library is created with Linux machines in mind but OSX users should not have a problem if they have gcc installed. I will try to compile an example with Visual Studio and get back to you on how to do it.
In order to get libartificial you have to do the following (assuming working installation of git)
git clone https://github.com/fetacore/libartificial.git cd libartificial rm -rf .git
For the time being I have four examples which you can find in the "examples" folder (assuming make and gcc):
- MLP regression (rbf like: gaussian & linear w/ RMSE):
- MLP classification (logistic & softmax w/ cross-entropy):
- CNN (only im2col at the moment):
If you want to compile them all then just do
If you like my work and/or you want to use it for your own projects or want me to create a custom recipe for you, I would gladly accept your donations at:
Copyright (c) Jim Karoukis. This project is licensed under the MIT License - see the LICENSE file for details.