CodeNewbie Community

Cover image for iNeural : A library for creating Artificial Neural Networks
Fatih Küçükkarakurt
Fatih Küçükkarakurt

Posted on

iNeural : A library for creating Artificial Neural Networks

iNeural, A library for creating Artificial Neural Networks, for use in Machine Learning and Deep Learning algorithms.

I have passed the first stage of this artificial neural network library, where I use the Eigen 3 library extensively. I continue to develop the project. You can check it out on my GitHub account.

I am preparing a very instructive and explanatory documentation that will explain the details of this project. Of course, I have a lot of updates to make, but I would like to point out that I will be releasing the API in the near future. Many tests with datasets such as CIFAR10, IRIS and MNIST were successful.

I would be very happy if you support this project and give stars. Great things will happen :)

Project Page => https://github.com/fkkarakurt/iNeural

Discussion (2)

Collapse
azaleakamellia profile image
Azalea

This looks very interesting! I'm new to machine learning and currently learning it for semantic segmentation -- beats the point-and-click tools that we use for satellite image classification. Is this restricted to image classification only? Is there any possibilities within it to delve into semantic segmentation?

Collapse
fkkarakurt profile image
Fatih Küçükkarakurt Author

iNeural is an open source library for artificial neural networks. It is open for users that want to apply ANN to their problems, developers and researchers that want to implement new technologies and students that want to understand the tricks that are required to implement neural networks. It follows a minimal dependency policy, i.e. it rely on only a few libraries and tools. It is not designed to use the full potential of GPUs though, but it is possible to run it on very limited systems, e.g. robotic platforms. Also, I'm still developing and making additions every day. I will have published the Documentation API in a very short time.

Thank you very much for your interest.