Compensating Resource Fluctuations by Means of Evolvable Hardware: The Run-Time Reconfigurable Functional Unit Row Classifier Architecture

The evolvable hardware (EHW) paradigm facilitates the construction of autonomous systems that can adapt to environmental changes and degradation of the computational resources. Extending the EHW principle to architectural adaptation, the authors study the capability of evolvable hardware classifiers to adapt to intentional run-time fluctuations in the available resources, i.e., chip area, in this work. To that end, the authors leverage the Functional Unit Row (FUR) architecture, a coarse-grained reconfigurable classifier, and apply it to two medical benchmarks, the Pima and Thyroid data sets from the UCI Machine Learning Repository. While quick recovery from architectural changes was already demonstrated for the FUR architecture, the authors also introduce two reconfiguration schemes helping to reduce the magnitude of degradation after architectural reconfiguration.

[1]  J. Torresen,et al.  Partial Reconfiguration Applied in an On-line Evolvable Pattern Recognition System , 2008, 2008 NORCHIP.

[2]  Hitoshi Iba,et al.  Evolving hardware with genetic learning: a first step towards building a Darwin machine , 1993 .

[3]  Moritoshi Yasunaga,et al.  On-Chip Evolution Using a Soft Processor Core Applied to Image Recognition , 2006, First NASA/ESA Conference on Adaptive Hardware and Systems (AHS'06).

[4]  Una-May O'Reilly,et al.  Genetic Programming Theory and Practice II , 2005 .

[5]  Michitaka Kosaka,et al.  A New Service Mediator For Human Resource Management , 2014, Int. J. Knowl. Syst. Sci..

[6]  Ingo Mierswa,et al.  YALE: rapid prototyping for complex data mining tasks , 2006, KDD '06.

[7]  BouaniFaouzi,et al.  Neural Networks Predictive Controller Using an Adaptive Control Rate , 2014 .

[8]  Moritoshi Yasunaga,et al.  An Online EHW Pattern Recognition System Applied to Face Image Recognition , 2009, EvoWorkshops.

[9]  Hossam A. Abdel Fattah,et al.  Adaptive Output Feedback Voltage-Based Control of Magnetically-Saturated Induction Motors , 2012, Int. J. Syst. Dyn. Appl..

[10]  Marco Platzner,et al.  EvoCaches: Application-specific Adaptation of Cache Mappings , 2009, 2009 NASA/ESA Conference on Adaptive Hardware and Systems.

[11]  John R. Koza,et al.  Routine high-return human-competitive evolvable hardware , 2004, Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004..

[12]  I. Yoshihara,et al.  Evolvable sonar spectrum discrimination chip designed by genetic algorithm , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[13]  Lukás Sekanina,et al.  Evolutionary Design Space Exploration for Median Circuits , 2004, EvoWorkshops.

[14]  Stephan M. Winkler,et al.  Using enhanced genetic programming techniques for evolving classifiers in the context of medical diagnosis , 2009, Genetic Programming and Evolvable Machines.

[15]  Mohammed Obaid Mustafa,et al.  International Journal of System Dynamics Applications , 2014 .

[16]  Moritoshi Yasunaga,et al.  Online Evolution for a High-Speed Image Recognition System Implemented On a Virtex-II Pro FPGA , 2007, Second NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2007).

[17]  Mehrdad Salami,et al.  Data Compression for Digital Color Electrophotographic Printer with Evolvable Hardware , 1998, ICES.

[18]  Nicoletta Sala,et al.  Complexity Science, Living Systems, and Reflexing Interfaces: New Models and Perspectives , 2012 .

[19]  Hugo de Garis,et al.  EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine , 1993 .

[20]  Lukas Sekanina,et al.  DESIGN OF THE SPECIAL FAST RECONFIGURABLE CHIP USING COMMON FPGA , 2001 .

[21]  Julian Francis Miller.  Cartesian Genetic Programming , 2011, Cartesian Genetic Programming.

[22]  Marco Platzner,et al.  Comparing Evolvable Hardware to Conventional Classifiers for Electromyographic Prosthetic Hand Control , 2008, 2008 NASA/ESA Conference on Adaptive Hardware and Systems.