A Reconfigurable Analog Neural Network for Evolvable Hardware Applications: Intrinsic Evolution and Extrinsic Verification

Continuous time recurrent neural networks (CTRNN) have been proposed for use as reconfigurable hardware for evolvable hardware (EH) applications. Our previous work demonstrated a fully programmable hardware CTRNN using off-the-shelf components and provided verification of its utility in extrinsic EH. However, applicability for intrinsic usage was not studied. This work addresses that unanswered issue and demonstrates that configurations evolved in the hardware are behaviorally equivalent to simplified state equation models. Further, this work also provides strong similarity metrics to compare the hardware's performance with software simulated CTRNN models.

[1]  Sanjay K. Boddhu,et al.  A reconfigurable continuous time recurrent neural network for evolvable hardware applications , 2005, 2005 IEEE Congress on Evolutionary Computation.

[2]  John C. Gallagher.  Evolution and analysis of non-autonomous neural networks for walking: reflexive pattern generators , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[3]  James M. Bower,et al.  Modeling Small Oscillating Biological Networks in Analog VLSI , 1988, NIPS.

[4]  Randall D. Beer,et al.  Evolution and Analysis of Model CPGs for Walking: II. General Principles and Individual Variability , 1999, Journal of Computational Neuroscience.

[5]  Randall D. Beer,et al.  Evolution and Analysis of Model CPGs for Walking: I. Dynamical Modules , 1999, Journal of Computational Neuroscience.

[6]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[7]  John C. Gallagher,et al.  The once and future analog alternative: evolvable hardware and analog computation , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..

[8]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[10]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[11]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[12]  Jack L. Meador,et al.  Programmable impulse neural circuits , 1991, IEEE Trans. Neural Networks.

[13]  Sanjay K. Boddhu,et al.  Evolving analog controllers for correcting thermoacoustic instability in real hardware , 2005, GECCO '05.

[14]  John C. Gallagher,et al.  A Modified Compact Genetic Algorithm For The Intrinsic Evolution Of Continuous Time Recurrent Neural Networks , 2002, GECCO.

[15]  J. C. Gallacher,et al.  Continuous time recurrent neural networks: a paradigm for evolvable analog controller circuits , 2000, Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No.00CH37093).

[16]  John C. Gallagher,et al.  On the relative efficacies of *cGA variants for intrinsic evolvable hardware; population, mutation, and random immigrants , 2004, Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004..