Damon A. Miller, Jacek M. Zurada  Home/Search
Context Related
| uofl.edu/zurada/pa...rZuradaTNN1998.pdf Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: uofl.edu/zurada/journal (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Structural learning with forgetting is an established method of using Laplace regularization to generate skeletal artificial neural networks. In this paper we develop a continuous dynamical system model of regularization in which the associated regularization parameter is generalized to be a time-varying function. Analytic results are obtained for a Laplace regularizer and a quadratic error surface by solving a different linear system in each region of the weight space. This model also enables... (Update)
Context of citations to this paper: More
.... structural learning with forgetting in which the small weights are dropped off through regularization parameters or decayed values [14]. The other way is using BackPropagation Through Time (BPTT) in which the number of parameters in the network can be confined with the memory...
Cited by: More
Mining Heterogeneous Gene Expression Data with Time Lagged.. - Liang, Kelemen (Correct)
Active bibliography (related documents): More All
0.5: Integration of Connectionist Methods and Chaotic.. - Kozma, Kasabov, Cohen (1998) (Correct)
0.2: Evolving Fuzzy Neural Networks for Supervised/Unsupervised.. - Kasabov (2001) (Correct)
0.2: Spatial-Temporal Adaptation in Evolving Fuzzy Neural Networks for .. - Kasabov (1999) (Correct)
Similar documents based on text: More All
0.2: Computational Intelligence Methods for Rule-Based Data.. - Duch, Setiono, Zurada (2004) (Correct)
0.2: IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 14, NO. 4, .. - Multistate Hopfield.. (2003) (Correct)
0.2: Extraction of Rules from Artificial Neural Networks for.. - Setiono, Leow, Zurada (2002) (Correct)
BibTeX entry: (Update)
Miller D. A., and Zurada, J. M. A dynamical system perspective of structural learning with forgetting, IEEE Transactions on Neural Networks, vol. 9, no. 3, pp. 508-515, 1998. http://citeseer.ist.psu.edu/miller98dynamical.html More
@article{ miller98dynamical,
author = "D. A. Miller and J. M. Zurada",
title = "A Dynamical System Perspective of Structural Learning with Forgetting",
journal = "IEEE Transactions on Neural Networks",
volume = "9",
number = "3",
month = "May",
pages = "508--515",
year = "1998",
url = "citeseer.ist.psu.edu/miller98dynamical.html" }
Citations (may not include all citations):1662 Neural Networks for Pattern Recognition (context) - Bishop - 1995
153 A practical Bayesian framework for backpropagation networks (context) - MacKay - 1992
111 Introduction to Artificial Neural Systems (context) - Zurada - 1992
86 Pruning algorithms---A survey (context) - Reed - 1993
55 Applied Linear Algebra (context) - Noble, Daniel - 1977
38 Advanced Methods in Neural Computing (context) - Wasserman - 1993
31 Bayesian regularization and pruning using a Laplace prior (context) - Williams - 1995
24 Structural learning with forgetting (context) - Ishikawa - 1996
6 Pruning via dynamic adaptation of the forgetting rate in str.. (context) - Miller, Zurada et al. - 1996
2 Dynamics of structural learning with an adaptive forgetting .. (context) - Miller, Zurada - 1997
1 Reconciling training and weight suppression: New guidelines .. (context) - Malinowski, Miller et al. - 1995
1 Dynamics of error backpropagation learning with pruning in t.. (context) - Lozowski, Miller et al. - 1996
Documents on the same site (http://ci.uofl.edu/zurada/journal.html): More
Special Issue - Pharmacodynamic Population Analysis (2003) (Correct)
Nonlinear Blind Source Separation Using a Radial Basis.. - Tan, Wang, Zurada (2001) (Correct)
Unknown - Ieee Transactions On (2004) (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