Learning method of non-linear network for non-linear function ap

Details Learning method of non-linear network for non-linear function ap Learning method of non-linear network for non-linear function ap

1994-08-09

1997-10-28

Hafiz, Tariq R.

395 21, G06E 100, G06F 1518

Patent

active

056824653

ABSTRACT:
A function approximation method is provided which is based on nonparametric estimation by using a network of three layers, such as an input layer, an output layer and a hidden layer. The input and the output layers have linear activation units while the hidden layer has nonlinear activation units which have the characteristics of bounds and locality. The whole learning sequence is divided to two phases. The first phase estimates the number of kernel functions based on a user's requirement on the desired level of accuracy of the network, and the second phase is related to parameter estimation. In the second phase, a linear learning rule is applied between output and hidden layers and a non-linear (piecewise-linear) learning rule is applied between hidden and input layers. Accordingly, an efficient way of function approximation is provided from the view point of the number of kernel functions as well as increased learning speed.

REFERENCES:
patent: 5058179 (1991-10-01), Denker et al.
patent: 5153923 (1992-10-01), Matsuba et al.
Moody, John et al.; "Fast Learning in Networks of Locally-Tuned Processing Units": Oct. 1988, pp.281-294; Yale Computer Science, New Haven, CT.
R. Scott Crowder, III; "Predicting the Mackey-Glass Timeseries with Cascade-Correlation Learning": pp. 117-123; School of Computer Science, Carnegie Mellon Univ., Pitts., PA.
Hwang et al, "Unsupervised learning . . . projection pursuit"; 1993 IEEE Internation Conference on Neural Networks, pp. 1486-1491 vol. 3, Mar. 1993.
Xu et al, "Kernel regression and radial basis . . . Theoretical studies"; IJCNN, pp. 818-823 vol. 1, Jun. 1992.
Lee et al, "Control of nonlinear system . . . function network"; 1991 IEEE International Conference on Neural Networks, pp. 1039-1046 vol. 2, Nov. 1991.
Ogawa et al, "Optimally Generalizing Neural Networks"; 1991 IEEE Internation Joint Conference on Neural Networks, pp. 2050-2055 vol. 3, Nov. 1991.

Affiliated with

Also associated with

Rating

Learning method of non-linear network for non-linear function ap does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Learning method of non-linear network for non-linear function ap, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning method of non-linear network for non-linear function ap will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1031369