On the Convergence of the LMS Algorithm with Adaptive Learning Rate for Linear Feedforword Networks

See this document in CiteSeerX!

On the Convergence of the LMS Algorithm with Adaptive Learning Rate for Linear Feedforword Networks (1990) (Make Corrections) (19 citations)
Zhi-Quan LuoNeural Computation

Home/Search Context Related

View or download:
crl.mcmaster.ca/People/Fa...backprop.ps
Cached: PDF PS.gz PS Image Update Help

From: crl.mcmaster.ca/People/Facu...luo (more)
(Enter author homepages)

Rate this article:

(best)
Comment on this article

(Enter summary)
Abstract: We consider the problem of training a linear feedforward neural network by using a gradient descent-- like LMS learning algorithm. The objective is to find a weight matrix for the network, by repeatedly presenting to it a finite set of examples, so that the sum of the squares of the errors is minimized. Kohonen showed that with a small but fixed learning rate (or stepsize) some subsequences of the weight matrices generated by the algorithm will converge to certain matrices close to the optimal... (Update)

Similar documents based on text: More All
0.1: Learning Curves for Stochastic Gradient Descent in Linear.. - Werfel, Xie, Seung (2003) (Correct)
0.0: Analysis Of An Approximate Gradient Projection Method With.. - Luo, Tseng (1994) (Correct)
0.0: A new solution for Boolean Circuit with DNA Computer - Qiu, Lu (2000) (Correct)

BibTeX entry: (Update)

Luo, Z.-Q. (1991). On the convergence of the lms algorithm with adaptive learning rate for linear feedfoward networks. Neural Computation, 2(3), 226-245. http://citeseer.ist.psu.edu/luo90convergence.html More

@article{ q91convergence,
    author = "Luo, Z.-Q.",
    title = "On the Convergence of the {LMS} Algorithm with Adaptive Learning Rate for Linear Feedforward Networks",
    journal = "Neural Computation",
    volume = "3",
    number = "2",
    pages = "226--245",
    year = "1991",
    url = "citeseer.ist.psu.edu/luo90convergence.html" }

Citations (may not include all citations):
1491 Learning Internal Representations by Error Propagation (context) - Rumelhart, Hinton et al. - 1986
700 Self--Organization and Associative Memory (context) - Kohonen - 1984
625 Parallel Distributed Processing--Explorations in the Microst.. (context) - Rumelhart, McClelland - 1986
256 Parallel Networks that Learn to Pronounce English Text (context) - Sejnowski, Rosenberg - 1987
222 Adaptive Switching Circuits (context) - Widrow, Hoff - 1960
175 Parallel and Distributed Computation (context) - Bertsekas, Tsitsiklis - 1989
162 Increased Rates of Convergence Through Learning Rate Adaptat.. (context) - Jacobs - 1988
115 Stochastic Approximation Method for Constrained and Unconstr.. (context) - Kushner, Clark - 1978
113 Analysis of Hidden Units in a Layered network Trained to Cla.. (context) - Gorman, Sejnowski - 1988
92 and Van Loan (context) - Golub - 1983
40 Some Asymptotic Results for Learning in Single Hidden Layer .. (context) - White - 1989
6 Asymptotic Convergence of Back propagation (context) - Tesauro, He et al. - 1989
4 A Modern Approach to Advanced Calculus (context) - Apostol - 1957
3 An Adaptive Associative Memory Principle (context) - Kohonen - 1974
2 Optimal and Robust Methods of Stochastic Optimization (context) - Tsypkin, Polyak - 1989

[Article contains additional citations not shown here]

The graph only includes citing articles where the year of publication is known.

Documents on the same site (http://www.crl.mcmaster.ca/People/Faculty/Luo/luo.html): More
Duality And Self-Duality For Conic Convex Programming - Luo, Sturm, Zhang (1996) (Correct)
Adaptive Decision Fusion for Distributed Detection - Mirjalily, Luo, Davidson.. (2000) (Correct)
Robust Filtering via Semidefinite Programming With.. - Lingjie Li Zhi-Quan (Correct)

Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback

CiteSeer.IST - Copyright Penn State and NEC