A neuromorphic controller with a human teacher

Trainable adaptive controllers (TACs) are a subset of process controllers in which much of the design is done online by means of training rather than programming. The authors show how a neural-network-based architecture may be used to implement a general-purpose TAC. An example of controlling a cart-pole system (an inverted pendulum mounted on a cart) is provided. It is found that filtering of the human-teacher training data, using a dynamic model of the teacher, significantly improves the neuromorphic TAC's performance.<<ETX>>

[1]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Stephen Grossberg,et al.  Absolute stability of global pattern formation and parallel memory storage by competitive neural networks , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Geoffrey E. Hinton,et al.  OPTIMAL PERCEPTUAL INFERENCE , 1983 .

[4]  A. Guez.  Optimal control of robotic manipulators , 1983 .

[5]  James A. Anderson,et al.  Cognitive and psychological computation with neural models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  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.

[8]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

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

[10]  Stephen Grossberg,et al.  Neural dynamics of adaptive sensory-motor control , 1986 .

[11]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[12]  Karl Johan Åström,et al.  Adaptive feedback control , 1987, Proc. IEEE.

[13]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[14]  Moshe Kam,et al.  NEUROMORPHIC ARCHITECTURE FOR ADAPTIVE ROBOT CONTROL: A PRELIMINARY ANALYSIS. , 1987 .

[15]  A. Guez,et al.  Neural network architecture for control , 1988, IEEE Control Systems Magazine.

[16]  A. Guez,et al.  A trainable neuromorphic controller , 1988 .

[17]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.