Steve Lawrence, Andrew D. Back, Ah Chung Tsoi, C. Lee Giles  Home/Search
Context Related
| nec.com/homepages/...ist.of.trials.ps.Z nec.com/homepages/...ltstnn97a4.ps.gz nec.com/homepages/...tnn97letter.ps.Z 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: nec.com/homepages/giles/papers... (more) From: nec.com/homepages/lawrenc...latex (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: The performance of neural network simulations is often reported in terms of the mean and standard deviation of a number of simulations performed with different starting conditions. However, in many cases, the distribution of the individual results does not approximate a Gaussian distribution, may not be symmetric, and may be multimodal. We present the distribution of results for practical problems and show that assuming Gaussian distributions can significantly affect the interpretation of... (Update)
Context of citations to this paper: More
.... The respective mean and standard deviation are not plotted, as none of the error distributions passed the Kolmogorov Smirnov Test([3]) comparing them to a Log Normal distribution. testbed physics mean Std.Dev Q1 median Q3 Min Max plain 0.2593 0.0878 0.2125 0.2489 0.2831...
Cited by: More
A Comparison of Informative and Discriminative Estimation of.. - Goodman (2000) (Correct)
Medically Motivated Testbed for Reinforcement Learning in .. - Surmeli, Köhler, Gross (1998) (Correct)
Similar documents (at the sentence level):
59.1%: On the Distribution of Performance from Multiple.. - Lawrence, Back, Tsoi.. (1997) (Correct)
27.9%: Presenting and Analyzing the Results of AI Experiments: Data.. - Giles, al. (1997) (Correct)
Active bibliography (related documents): More All
0.3: What Size Neural Network Gives Optimal Generalization?.. - Lawrence, Giles, Tsoi (1996) (Correct)
0.2: The Role of Occam's Razor in Knowledge Discovery - Domingos (1999) (Correct)
0.2: Applying Simple Combining Techniques with Artificial.. - Sancho.. (Correct)
Similar documents based on text: More All
2.4: Neural Network Classification and Prior Class.. - Lawrence, Burns, Back.. (1998) (Correct)
2.0: The Gamma model - a new neural network for temporal processing - Vries (1992) (Correct)
1.7: Face Recognition: A Hybrid Neural Network Approach - Lawrence, Giles, Tsoi, Back (1996) (Correct)
BibTeX entry: (Update)
Steve Lawrence, Andrew D. Back, Ah Chung Tsoi, and C. Lee Giles. On the distribution of performance from multiple neural network trials. IEEE Transactions on Neural Networks (IEEE TNN), accepted, 1997. http://citeseer.ist.psu.edu/article/lawrence97distribution.html More
@article{ lawrence97distribution,
author = "S. Lawrence and A. D. Back and A. C. Tsoi and C. L. Giles",
title = "On the Distribution of Performance from Multiple Neural-Network Trials",
journal = "IEEE Transactions on Neural Networks",
volume = "8",
number = "6",
month = "November",
pages = "1507--1517",
year = "1997",
url = "citeseer.ist.psu.edu/article/lawrence97distribution.html" }
Citations (may not include all citations):1535 Cambridge University Press (context) - Press, Teukolsky et al. - 1992
471 and Stochastic Processes (context) - Papoulis, Random - 1991
176 Exploratory Data Analysis (context) - Tukey - 1977
127 Oscillation and chaos in physiological control systems (context) - Mackey, Glass - 1977
102 Training a 3-node neural network is NP-complete - Blum, Rivest - 1992
90 Neural Network Design and the Complexity of Learning (context) - Judd - 1990
79 A Comprehensive Foundation (context) - Haykin - 1994
34 An economics approach to hard computational problems (context) - Huberman, Lukose et al. - 1997
33 Note on learning rate schedules for stochastic optimization (context) - Darken, Moody - 1991
29 Complexity results on learning by neural nets - Lin, Vitter - 1991
24 Back propagation fails to separate where perceptrons succeed (context) - Brady, Raghavan et al. - 1989
23 the complexity of loading shallow neural networks (context) - Judd - 1988
22 a new neural network architecture for time series modeling (context) - Back, Tsoi et al. - 1991
20 Exponentially many local minima for single neurons - Auer, Herbster et al. - 1996
20 Statistical evaluation of neural network experiments: Minimu.. - Flexer - 1995
17 Mathematical Theory of Probability and Statistics (context) - von Mises - 1964
14 Chaotic attractors of an infinite-dimensional dynamical syst.. (context) - Farmer - 1982
12 A unifying view of some training algorithms for multilayer p.. - Back, Wan et al. - 1995
11 Strong universal consistency of neural network classifiers (context) - Farago, Lugosi - 1993
10 Results of the time series prediction competition at the San.. (context) - Weigend, Gershenfeld - 1993
9 Introductory Statistics (context) - Weiss, Hassett - 1987
8 New Techniques for Nonlinear System Identification: A Rappro.. (context) - Back - 1992
6 An efficient algorithm for the Kolmogorov-Smirnov and Lillie.. (context) - Gonzalez, Sahni et al. - 1977
5 Characterizing neural network error surfaces with a sequenti.. (context) - Crane, Fefferman et al. - 1995
4 Lessons in neural network training: Overfitting may be harde.. - Lawrence, Giles et al. - 1997
3 A statistical neural network for high-dimensional vector cla.. - Verleysen, Voz et al. - 1995
Documents on the same site (http://www.neci.nj.nec.com/homepages/giles/papers/): More
An Analysis of Noise in Recurrent Neural Networks.. - Jim, Giles, Horne (1996) (Correct)
Product Unit Learning - Leerink, Giles, Horne, Jabri (Correct)
Neural Learning of Chaotic Dynamics: The Error.. - Rembrandt Bakker.. (1997) (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