Widrow

Widrow, B. (1987) The Original Adaptive Neural Net Broom-Balancer. In Proc. IEEE Int. Symp. Circuits and Systems, pp. 351-357. 

Widrow, B. and Hoff, M.E. (1960) Adaptive switching circuits. In IEEE WESCON Convention Record, IRE, New York, pp. 96-104. 

Widrow, B. and Smith, F.W. (1964) Pattern recognising control systems. In Computer and Information Sciences, Ton, J.T. and Wilcox, R.H. (eds.), Spartan Books, Cleaver Hume Press, pp. 288-317. 

Other rules are of course possible. One popular choice called the Delta Rule was introduced in 1960 by Widrow and Hoff ([widrowGO], [widrow62]). Their idea was to adjust the weights in proportion to the error (= A) between the desired output (= D(t)) and the actual output (= y(t)) of the perceptron ... 

Widrow and Steams, 1985] Widrow, B. and Steams, S. (1985). Adaptive Signal Processing. Prentice Hall, Englewood Cliffs, NJ. 

There are modifications to the perceptron learning rule to help effect faster convergence. The Widrow-Hoff delta rule (Widrow Hoff, 1960) multiplies the delta term by a number less than 1, called the learning rate, tv This effectively causes smaller changes to be made at each step. There are heuristic rules to decrease T] as training time increases the idea is that big changes may be taken at first and as the final solution is approached, smaller changes may be desired. 

A recent survey (27) touched on several other applications AIWARE has built a system which troubleshoots grinding operations in a factory Global Holonetics LIGHTWARE performs quality control on an assembly line Widrow has developed a neural network which eliminates echoes in telephone lines, and is used in modems and other signaling devices Carleton University s Neuroplanner is a set of networks which enables a robot to navigate its workspace. 

Widrow, B., and S. D. Stearns. 1985. Adaptive signal processing. Englewood Cliffs, NJ Prentice Hall, Inc. 

Fulop M, Widrow DR, Colmers RA, Epstein EJ. Possible diiihenylhydantoin-induced arrhythmia in hypothyroidism. JAMA (1966) 196, 454-6. 

Artificial neural networks are machine-based learning models and were first developed by Bernard Widrow of Stanford University in the 1950s. They have the ability to learn and process information in a wider context than simple nonalgorithmic or rule-based systems, thus allowing them to successfully simulate human reasoning (Bishop, 1995). 

Nguyen, D.H. and Widrow, B. 1990. Neural networks for self-learning control systems. IEEE Contr. Syst. Mag., 10 18-23. 

Widrow, B. 1962. Generalization and information storage in networks of adahne neurons. In Self-Organizing Systems. M.C. Jovitz, T. Jacobi, and Goldstein, Eds. pp. 435-461. Spartan Books, Washington, D.C. 

---