Title :
The Widrow-Hoff algorithm for McCulloch-Pitts type neurons
Author :
Hui, Stefen ; Zak, Stanislaw H.
Author_Institution :
Dept. of Math. Sci., San Diego State Univ., CA, USA
fDate :
11/1/1994 12:00:00 AM
Abstract :
We analyze the convergence properties of the Widrow-Hoff delta rule applied to McCulloch-Pitts type neurons. We give sufficiency conditions under which the learning parameters converge and conditions under which the learning parameters diverge. In particular, we analyze how the learning rate affects the convergence of the learning parameters
Keywords :
adaptive systems; learning (artificial intelligence); neural nets; parallel algorithms; McCulloch-Pitts type neurons; Widrow-Hoff algorithm; Widrow-Hoff delta rule; convergence; learning parameters; learning rate; neural networks; sufficiency conditions; Adaptive algorithm; Algorithm design and analysis; Bridges; Convergence; Error correction; Iterative algorithms; Neurons;
Journal_Title :
Neural Networks, IEEE Transactions on
