CompoNet: Programmatically Embedding Neural Networks into AI Applications as Software Components

The provision of embedding neural networks into software applications can enable variety of artificial intelligence systems for individual users as well as organizations. Previously, software implementation of neural networks remained limited to only simulations or application specific solutions. Tightly coupled solutions end up in monolithic systems and non reusable programming efforts. We adapt component based software engineering approach to effortlessly integrate neural network models into AI systems in an application independent way. As proof of concept, this paper presents componentization of three famous neural network models i) multi layer perceptron ii) learning vector quantization and iii) adaptive resonance theory family of networks.

[1]  Bernard Girau,et al.  NSK, an object-oriented simulator kernel for arbitrary feedforward neural networks , 1994, Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94.

[2]  S. H. Huang,et al.  Artificial neural networks in manufacturing: concepts, applications, and perspectives , 1994 .

[3]  George S. Moschytz,et al.  An interactive object-oriented neural network simulator applied to the recognition of acoustical signals , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.

[4]  Jun Yang,et al.  Isolated speech recognition using artificial neural networks , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[6]  Sungyoung Lee,et al.  A Rapid Development Approach for Signal Strength Based Location Systems , 2007 .

[7]  Daikui Shouren Hu,et al.  An object-oriented neural network language , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[8]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[9]  Majid Ahmadi,et al.  N-feature neural network human face recognition , 2004, Image Vis. Comput..

[10]  H. Takatama,et al.  Field Experiment of an Extendable Traceability System: Application to the Quality Control of Beef-Product Distribution , 2007 .

[11]  F. B. Khalafalla,et al.  Object oriented neural networks , 1991 .

[12]  Bernabé Linares-Barranco,et al.  Adaptive Resonance Theory Microchips , 1999, IWANN.

[13]  S. Isotani,et al.  The adherence of the object oriented programming paradigm on the simulation of artificial neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[14]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[15]  A. G. Phadke,et al.  Artificial neural networks in power system restoration , 2002 .

[16]  R. Vitthal,et al.  Process control via artificial neural networks and learning automata , 1995, Proceedings of IEEE/IAS International Conference on Industrial Automation and Control.

[17]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[18]  Jens Rasmussen,et al.  The role of hierarchical knowledge representation in decisionmaking and system management , 1985, IEEE Transactions on Systems, Man, and Cybernetics.