OpenNN
| OpenNN | |
|---|---|
| File:Opennn standard logo.svg | |
| Developer(s) | Intelnics |
| Repository | |
| Operating system | Cross-platform |
| Type | Neural networks |
| License | LGPL |
| Website | http://www.intelnics.com/opennn |
OpenNN (Open Neural Networks Library) is a software library written in the C++ programming language which implements neural networks,[1] a main area of deep learning research. The library is open source, hosted at SourceForge and licensed under the GNU Lesser General Public License.
Characteristics
The software 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 increse the computer performance.
OpenNN contains data mining algorithms as a bundle of functions. 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 functions can be supported by specific visualization tools.[2]
History
The development started in 2003 at the International Center for Numerical Methods in Engineering (CIMNE), within the research project funded by the European Union called RAMFLOOD.[3] Then it continued as part of similar projects. At present, OpenNN is being developed by the startup company Intelnics.[4]
In 2014, Big Data Analytics Today rated OpenNN as the #1 brain inspired artificial intelligence project.[5] Also, during the same year, ToppersWorld selected OpenNN among the top 5 open source data mining tools.[6]
Applications
OpenNN is a general purpose artificial intelligence software package.[7] It uses machine learning techniques for solving data mining and predictive analytics tasks in different fields. For instance, the library has been applied in the engineering,[8] energy,[9] or chemistry[10] sectors.
Related libraries
- Deeplearning4j, a deep learning library written for Java and Scala which is open source.
- Torch, an open source framework written in Lua with wide support for machine learning algorithms.
See also
References
- ^ "OpenNN, An Open Source Library For Neural Networks". KDNuggets. June 2014.
- ^ J. Mary Dallfin Bruxella; et al. (2014). "Categorization of Data Mining Tools Based on Their Types". International Journal of Computer Science and Mobile Computing. 3 (3): 445–452.
{{cite journal}}: Explicit use of et al. in:|author=(help) - ^ "CORDIS - EU Research Project RAMFLOOD". European Commission. December 2004.
- ^ "Intelnics home page".
- ^ "Top 12 Brain Inspired Artificial Intelligence Projects". Big Data Analytics Today. October 2014.
- ^ "Top 5 Open Source Data Mining Tools". ToppersWorld. November 2014.
- ^ "Here Are 7 Thought-Provoking AI Software Packages For Your Info". Saurabh Singh. Retrieved 25 June 2014.
- ^ R. Lopez; et al. (2008). "Neural Networks for Variational Problems in Engineering". International Journal for Numerical Methods in Engineering. 75 (11): 1341–1360. doi:10.1002/nme.2304.
{{cite journal}}: Explicit use of et al. in:|author=(help) - ^ P. Richter; et al. (2011). "Optimisation of Concentrating Solar Thermal Power Plants with Neural Networks". Lecture Notes in Computer Science. 6593: 190–199. doi:10.1007/978-3-642-20282-7_20.
{{cite journal}}: Explicit use of et al. in:|author=(help) - ^ A.A. D’Archivio; et al. (2014). "Artificial Neural Network Prediction of Multilinear Gradient Retention in Reversed-Phase HPLC". Analytical and Bioanalytical Chemistry. 407: 1–10. doi:10.1007/s00216-014-8317-3.
{{cite journal}}: Explicit use of et al. in:|author=(help)