A genetic algorithm as the learning procedure for neural networks

A way in which a neural network can implement a genetic algorithm as its learning algorithm is shown. This model is called GLANN (genetic learning algorithm for neural networks). The components of GLANN can be shown to be biologically plausible. The algorithm itself can be classified as a reinforcement learning algorithm. The neural network has a fixed architecture and processes binary strings using genetic operators. Learning is stored in the form of newly created patterns, which can then be stored in some kind of associative memory. The benefits of GLANN reside in the proven optimizing capabilities of genetic algorithms, and in its parallel implementation. The shallow two-level architecture translates into system scalability, an issue that has not been successfully resolved in the case of other neural network algorithms.<<ETX>>

[1]  Michael Smith.  An analog integrated neural network capable of learning the Feigenbaum logistic map , 1990 .

[2]  F. Pongrácz,et al.  The function of dendritic spines: A theoretical study , 1985, Neuroscience.

[3]  Dale Purves,et al.  Trophic regulation of nerve cell morphology and innervation in the autonomic nervous system , 1988, Nature.

[4]  Eugene M. Strand,et al.  A neural network for tracking the prevailing heart rate of the electrocardiogram , 1990, [1990] Proceedings. Third Annual IEEE Symposium on Computer-Based Medical Systems.

[5]  Fathi M. A. Salam,et al.  On the analysis of dynamic feedback neural nets , 1991 .

[6]  Shi Bai,et al.  A new feedback neural network with supervised learning , 1991, IEEE Trans. Neural Networks.

[7]  Hyongsuk Kim,et al.  CMAC-based adaptive critic self-learning control , 1991, IEEE Trans. Neural Networks.

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  W. T. Miller,et al.  CMAC: an associative neural network alternative to backpropagation , 1990, Proc. IEEE.

[10]  Malur K. Sundareshan,et al.  Equilibrium characterization of dynamical neural networks and a systematic synthesis procedure for associative memories , 1991, IEEE Trans. Neural Networks.

[11]  W. Hubbard,et al.  A programmable analog neural network chip , 1989 .

[12]  E. M. Strand,et al.  Tracking ventricular arrhythmias with an artificial neural network , 1990, [1990] Proceedings Computers in Cardiology.

[13]  Nabil H. Farhat.  Microwave diversity imaging and automated target identification based on models of neural networks , 1989 .

[14]  N. Sloane,et al.  Hadamard transform optics , 1979 .

[15]  R. M. Holdaway.  Enhancing supervised learning algorithms via self-organization , 1989, International 1989 Joint Conference on Neural Networks.

[16]  H. Tuckwell.  Introduction to Theoretical Neurobiology: Linear Cable Theory and Dendritic Structure , 1988 .

[17]  L.G. Kraft,et al.  A comparison between CMAC neural network control and two traditional adaptive control systems , 1990, IEEE Control Systems Magazine.

[18]  Jose B. Cruz,et al.  Two coding strategies for bidirectional associative memory , 1990, IEEE Trans. Neural Networks.

[19]  Donald E. Knuth,et al.  Sorting and Searching , 1973 .

[20]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[21]  Klaus Schumacher,et al.  VLSI technologies for artificial neural networks , 1989, IEEE Micro.

[22]  S B Udin,et al.  Formation of topographic maps. , 1988, Annual review of neuroscience.

[23]  T. Bliss,et al.  NMDA receptors - their role in long-term potentiation , 1987, Trends in Neurosciences.

[24]  Y.-F. Wang,et al.  An enhanced bidirectional associative memory , 1989, International 1989 Joint Conference on Neural Networks.

[25]  Russell Leighton,et al.  Shaping schedules as a method for accelerated learning , 1988, Neural Networks.

[26]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[27]  F.M.A. Salam.  A formulation for the design of neural processors , 1988, IEEE 1988 International Conference on Neural Networks.

[28]  Bart Kosko,et al.  Unsupervised learning in noise , 1990, International 1989 Joint Conference on Neural Networks.

[29]  Francis D. Murnaghan,et al.  The theory of group representations , 1938 .

[30]  Jose B. Cruz,et al.  Guaranteed recall of all training pairs for bidirectional associative memory , 1991, IEEE Trans. Neural Networks.

[31]  Bing J. Sheu,et al.  Design of a neural-based A/D converter using modified Hopfield network , 1989 .

[32]  Kosko.  Unsupervised learning in noise , 1989 .

[33]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[34]  H. C. LONGUET-HIGGINS,et al.  Non-Holographic Associative Memory , 1969, Nature.

[35]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[36]  Idan Segev,et al.  Signal enhancement in distal cortical dendrites by means of interactions between active dendritic spines. , 1985, Proceedings of the National Academy of Sciences of the United States of America.

[37]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[38]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .

[39]  W. Thomas Miller,et al.  Sensor-based control of robotic manipulators using a general learning algorithm , 1987, IEEE J. Robotics Autom..

[40]  Nabil H. Farhat,et al.  Learning networks for extrapolation and radar target identification , 1992, Neural Networks.

[41]  P. Dicke,et al.  Feature linking via stimulus-evoked oscillations: experimental results from cat visual cortex and functional implications from a network model , 1989, International 1989 Joint Conference on Neural Networks.