Adaptive neuron model--an architecture for the rapid learning of

Details Adaptive neuron model--an architecture for the rapid learning of Adaptive neuron model--an architecture for the rapid learning of

1992-08-28

1994-12-06

MacDonald, Allen R.

395 21, 395 24, 395 25, G06F 1518

Patent

active

053718348

ABSTRACT:
A method and an apparatus for the rapid learning of nonlinear mappings and topological transformations using a dynamically reconfigurable artificial neural network is presented. This fully-recurrent Adaptive Neuron Model (ANM) network has been applied to the highly degenerative inverse kinematics problem in robotics, and its performance evaluation is bench-marked. Once trained, the resulting neuromorphic architecture was implemented in custom analog neural network hardware and the parameters capturing the functional transformation downloaded onto the system. This neuroprocessor, capable of 10.sup.9 ops/sec, was interfaced directly to a three degree of freedom Heathkit robotic manipulator. Calculation of the hardware feed-forward pass for this mapping was benchmarked at .apprxeq.10 .mu.sec.

REFERENCES:
patent: 4897811 (1970-01-01), Scofield
patent: 4914708 (1990-04-01), Carpenter et al.
patent: 4990838 (1991-02-01), Kawato et al.
Computational Complexity Reduction for Neural Network Algorithms Allon Guez Apr. 1989 IEEE pp. 409-414.
Optimal Simulated annealing method and its application to combinatorial problems IEEE, Ikuo Matsura, IEEE, pp. 541-546.
Structural Stability of Unsupervised Learning in Feedback Neural Networks Bart Kosko IEEE, pp. 785-792 7 Jul. 1991.
M. Gherrity, A Learning algorithm for analog fully recurrent neural networks, IEEE 18-22 Jun. 1989 pp. 643-644.
A Stochastic High-Order Connectionist network for solving Interferencing problems, C. L. Masti, IEEE 18-21 Nov. 1991 pp. 911-916.
Learning of the Conlomb Energy Network on the variation of Temperature H. S. Choi, IEEE 7-11 Jun. 1992 pp. 749-754.
Neurocomputing R. H. Nielsen Addison-Wesley 1990 pp. 78-79; 164-167.
Richard P. Lippmann. An introduction to computing with neural network. IEEE ASSP magazine, pp. 4-22, 1987.
Jacob Barhen, Michael Zak, and Sandeep Gulati. Fast neural learning algorithms using networks with non-lipschitzian dynamics.
In Proceedings of Neuro-Nimes '89, 1989. Nimes, France.
Michael Zak. Terminal attractors for addressable memory in neural networks. Physical Letters A, 133:218-222, 1988.
John Moody and C Darken. Fast learning in neural networks of locally-tuned processing units. Neural Computation, 1 (2), 1989.
John Platt. A resource-allocating neural network for function interpolation. Neural Computation, 3(2), 1991.
Scott E. Fahlman and Christian Lebiere. The cascade-correlation learning architecture. In Advances in Neural Information Processing Systems, 1990. Denver, Colo.
Mark Holler, Simon Tam Hernan Castro, and Ronald Benson. An electrically trainable artificial neural network (etann) with 10240 `floating gate` synapses. In Proceedings of the IJCNN, 1989. Washington, D.C.
Raoul Tawel. Does the neuron `learn` like the synapse. In Advances in Neural Information Processing Systems, vol. 1, San Mateo California, 1989. Morgan Kaufmann Publishers.
Raoul Tawel. Adaptive neurons for artificial neural networks. Applied Optics, 30:1000, 1991.
Michael I. Jordan. Supervised learning and systems with exces degrees of freedom. Technical Report 88-27, University of Massachusetts at Amerst, 1988.
A. Guez. Solution to the inverse kinematic problem in robotics by neural networks. In Proceedings of the 2nd International Conference on Neural Networks, 1988. San Diego, California.
Gary Josin. Neural-space generalization of a topological transformation. Biological Cybernetics, 59, 1988.
Jacob Barhen, Sandeep Gulati, and Michael Zak. Neural learning of inverse kinematics for redundant manipulators in unstructured environments. IEEE Computer, Jun., 1989.
Bartlett W. Mel. Murphy: A robot that learns by doing. In Neural Information Processing Systems, New York, NY, 1988. American Institute of Physics.
Raoul Tawel, Silvio Peter Eberhardt, and Anil P. Thakoor. Neural networks for robotic control. In Proceedings of Conference on Neural Networks for Computing, 1988. Snowbird, Utah.
Michael Kuperstein. Neural netork model for adaptive hand-eye coordination for single postures. Science, 239; 1308-1311, 1988.
Michael Kuperstein. Implementation of an adaptive neural controller for sensory-motor coordination. In Proceedings of the 2nd International Conference on Neural Networks, 1988. San Diego, California.
J S Albus. A new approach to manipulator control: the cerebeller model articulation controller (cmac). ASME journal of Dynamic Systems, Measurement, and Control, pp. 220-227, 1975.
W. Thomas Miller, Filson H. Glanz, and L. Gordon Kraft. Application of a general learning algoithm to the control of robotic manipulators. The International Journal of Robotic Research, 6, 1987.
W. Thomas Miller, Robert P. Hewes, Filson H. Glanz, and L. Gordon Kraft. Real time dynamic control of an industrial manipulator using a neural network based learning controller. IEEE Journal of Robotics and Automation, 1988.
Rolf Eckmiller, Jurgen Beckman, Heinz Werntges, and Martin Lades. Neural kinetics net for a redundant robot arm. In Proceedings of the 1st Joint Conference on Neural Networks, 1989. Washington D.C.
Raoul Tawel and Anil Prakash Thakoor. Neural network hardware solution to the inverse kinematic problem in robotics In Proceeding of the IEEE Third Annual Processing Symposium, 1989 Fullerton, California.
Silvio Peter Eberhardt, TuanDuong, and Anil Prakash Thakoor. A visi synapse `building block` chip for hardware neural network implementations. In Larry H. Canter, editor, IEEE 3rd Annual Parallel Processing Symposium, 1989. Fullerton, California.
Fernando J. Pineda. Generalization of backpropagation to recurrent neural networks Phys. Rev. Lett, 18, 1987.
Fernando J. Pineda. Generalization of backpropagation to recurrent and higher order neural networks. In Proceedings of the Neural Information Processing Systems Conference, 1987.
John J. Craig. Introduction Robotic Mechanisms and Control. Addison-Wesley Publishing Co., REading, Massachusetts, 1986 pp. 113-151 2nd Edition.
Richard P. Paul. Robot Manipulators: Mathematics, Programming, and Control. MIT Press, Cambridge, Massachusetts, 1981. pp. 119-155.
William H. Press, Brian P. Flannery, Saul A. Teukolsky, and William T. Vetterling. Numerical recipes in C. The art of scientific computing. Cambridge University Press, Cambridge, England, 1988. pp. 85-91.
Alex Moopenn, Anil Prakash Thakoor, and Tuan Duong. Digital-analog hybrid neural simulator: A design aid for custom visi neurochips. In K. Bromley, editor, Proceedings of the SPIE Conference on High Speed Computing, 1989. Los Angeles, California.
Silvio Peter Eberhardt, Tuan Duong, and Anil Prakash Thakoor. Design of Parallel hardware neural network systems form custom analog visi building block chips. In Proceedings of the IJCNN, 1989. Washington, D.C.
Raoul Tawel and Anil P. Thakoor. Neural solutions to robotic control tasks and their hardware implementation. In Proceedings of the International Neural Network Society, 1988. Boston, Massachusetts.
Raoul Tawel. Learning in analog neural network hardware. In Proceedings of the Ascona workshop on industrial applications of neural networks, 1991. Ascona, Switzerland.
Silvio P. Eberhardt, Tuan Duong, Raoul Tawel, Fernando J. Pineda, and Anil P. Thakoor. A robotics inverse kinematics problem neural network hardware with gradient-descent learning. In Proceedings of IASTED International Conference on Expert Systems and Neural Networks, vol. 123, 1990. Honolulu, Hawaii.

Affiliated with

Also associated with

Rating

Adaptive neuron model--an architecture for the rapid learning of does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Adaptive neuron model--an architecture for the rapid learning of, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive neuron model--an architecture for the rapid learning of will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-221016