-
- Description:
OpenNN is an open source class library written in C++ programming language which implements neural networks, a main area of deep learning research. It is intended for advanced users, with high C++ and machine learning skills.
The library implements any number of layers of non-linear processing units for supervised learning. This deep architecture allows the design of neural networks with universal approximation properties. On the other hand, it allows multiprocessing programming by means of OpenMP, in order to increase the computer performance.
OpenNN contains data mining algorithms as a bundle of classes. These can be embedded in other software tools, using an application programming interface, for the integration of the predictive analytics tasks. In this regard, a graphical user interface is missing but some methods are supported by specific visualization tools.
The package comes with unit testing, many examples and extensive documentation. Some typical applications for OpenNN are function regression (modelling), pattern recognition (classification), time series prediction (forecasting) and auto association.
OpenNN is developed by Artelnics, a company specialized in artificial intelligence.
- Changes to previous version:
New algorithms, correction of bugs.
- BibTeX Entry: Download
- Corresponding Paper BibTeX Entry: Download
- Supported Operating Systems: Linux, Windows, Mac Os
- Data Formats: Space Separated Values
- Tags: Neural Networks, Machine Learning, Data Mining, Big Data
- Archive: download here
Comments
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.