A Fully-Connected Micro-extended Analog Computers Array Optimized by Particle Swarm Optimizer

The micro-Extended Analog ComputeruEAC is a novel hardware implementation of Rubel's EAC model. In this study, we first analyse the basic uEAC mathematical model and two uEAC extensions with minus-feedback and multiplication-feedback, respectively. Then a fully-connected uEACs array is proposed to enhance the computational capability, and to get an optimal uEACs array structure for specific problems, a comprehensive optimization strategy based on Particle Swarm OptimizerPSO is designed. We apply the proposed uEACs array to Iris pattern classification database, the simulation results verify that all the uEACs array parameters can be optimized simultaneously, and the classification accuracy is relatively high.

[1]  Jonathan W. Mills,et al.  The continuous retina: image processing with a single-sensor artificial neural field network , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[2]  James S. Small.  General-purpose electronic analog computing: 1945-1965 , 1993, IEEE Annals of the History of Computing.

[3]  Jonathan W. Mills,et al.  CMOS VLSI Lukasiewicz logic arrays , 1990, [1990] Proceedings of the International Conference on Application Specific Array Processors.

[4]  Ben Goertzel,et al.  A world survey of artificial brain projects, Part II: Biologically inspired cognitive architectures , 2010, Neurocomputing.

[5]  D. Lebell.  The Differential Analyzer , 1952 .

[6]  A. Turing.  On Computable Numbers, with an Application to the Entscheidungsproblem. , 1937 .

[7]  Jonathan W. Mills,et al.  The nature of the Extended Analog Computer , 2008 .

[8]  Itamar Arel,et al.  DeSTIN: A Scalable Deep Learning Architecture with Application to High-Dimensional Robust Pattern Recognition , 2009, AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.

[9]  de GarisHugo,et al.  A world survey of artificial brain projects, Part II , 2010 .

[10]  A. Turing,et al.  On Computable Numbers, with an Application to the Entscheidungsproblem. A Correction , 1938 .

[11]  Jerzy Mycka,et al.  Analog computation beyond the Turing limit , 2006, Appl. Math. Comput..

[12]  Bryce Himebaugh,et al.  Lukasiewicz' Insect: Continuous-Valued Robotic Control After Ten Years , 2003, J. Multiple Valued Log. Soft Comput..

[13]  Claude E. Shannon,et al.  Mathematical Theory of the Differential Analyzer , 1941 .

[14]  Ben Goertzel,et al.  A world survey of artificial brain projects, Part I: Large-scale brain simulations , 2010, Neurocomputing.

[15]  Jonathan Wayne Mills,et al.  Lukasiewicz logic arrays , 1990, Proceedings of the Twentieth International Symposium on Multiple-Valued Logic.

[16]  Lee A. Rubel,et al.  The Extended Analog Computer , 1993 .

[17]  Vannevar Bush,et al.  The differential analyzer. A new machine for solving differential equations , 1931 .

[18]  Chen Zhang,et al.  Evolving Letter Recognition with an Extended Analog Computer , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[19]  John Brooks.  Dreadnought Gunnery and the Battle of Jutland: The Question of Fire Control , 2005 .

[20]  Rui Zhang,et al.  The research on the application of uEAC in XOR problems , 2011, Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE).

[21]  Xuemei Ren,et al.  Optimization of Multi-Micro Extended Analog Computer Array and its Applications to Data Mining , 2014, Int. J. Unconv. Comput..