Self-organizing learning array

• Published in: IEEE transactions on neural networks Vol. 16; no. 2; pp. 355 - 363
• Main Authors: Starzyk, J.A., Zhen Zhu, Tsun-Ho Liu
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.2005; Institute of Electrical and Electronics Engineers
• Subjects: Adaptive systems; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Connectionism. Neural networks; Entropy; Estimation theory; Exact sciences and technology; Hardware; Information theory-based machine learning; Learning; Machine learning; multilayer learning array; Neural Networks (Computer); Neurons; Neurons - physiology; Nonhomogeneous media; Scalability; self-organizing neurons; System testing; Wiring; Concept learning; Self learning; Statistical analysis; Probabilistic approach; Scalability; Adaptive system; Neural network; Wiring; Self organization; Classification; Reconfigurable architectures; Artificial intelligence; Information theory
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/TNN.2004.842362

A new machine learning concept-self-organizing learning array (SOLAR)-is presented. It is a sparsely connected, information theory-based learning machine, with a multilayer structure. It has reconfigurable processing units (neurons) and an evolvable system structure, which makes it an adaptive classification system for a variety of machine learning problems. Its multilayer structure can handle complex problems. Based on the entropy estimation, information theory-based learning is performed locally at each neuron. Neural parameters and connections that correspond to minimum entropy are adaptively set for each neuron. By choosing connections for each neuron, the system sets up its wiring and completes its self-organization. SOLAR classifies input data based on the weighted statistical information from all the neurons. The system classification ability has been simulated and experiments were conducted using test-bench data. Results show a very good performance compared to other classification methods. An important advantage of this structure is its scalability to a large system and ease of hardware implementation on regular arrays of cells.