Helmut A. Mayer, Roland Schwaiger  Home/Search
Context
Related
| cosy.sbg.ac.at/project/...porto01.ps.gz 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: cosy.sbg.ac.at/project/sigis/P... (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: The most common (or even only) choice of activation functions (AFs) for multi{layer perceptrons (MLPs) widely used in research, engineering and business is the logistic function. Among the reasons for this popularity are its boundedness in the unit interval, the function's and its derivative's fast computability, and a number of amenable mathematical properties in the realm of approximation theory. However, considering the huge variety of problem domains MLPs are applied in, it is intriguing to ... (Update)
Similar documents (at the sentence level):
50.7%: Differentiation of Neuron Types by Evolving Activation.. - Mayer, Schwaiger (2002) (Correct)
8.4%: Simultaneous Evolution of Structure and Activation.. - Mayer, Strapetz, Fuchs (2001) (Correct)
Active bibliography (related documents): More All
0.3: Maximizing the Margin with Feed-forward Neural - Networks Enrique Romero (Correct)
0.3: On Optimal Pairwise Linear Classifiers for Normal.. - Rueda, Oommen (2002) (Correct)
0.0: Fast Complex Adaptive Spline Neural Networks for.. - Uncini, Capparelli.. (1998) (Correct)
Similar documents based on text: More All
1.8: Evolutionary and Coevolutionary Approaches to Time Series.. - Mayer, Schwaiger (1999) (Correct)
1.7: Towards The Evolution of Training Data Sets for Artificial.. - Mayer, Schwaiger (1997) (Correct)
1.6: Land Cover Classification of Landsat Images Using.. - Schwaiger, al. (1995) (Correct)
BibTeX entry: (Update)
@INPROCEEDINGS(Mayer01d,
AUTHOR = "Helmut A. Mayer and Roland Schwaiger",
TITLE = "{Evolution of Cubic Spline Activation Functions for Artificial
Neural Networks}",
BOOKTITLE = "Proceedings of the 10th Portuguese Conference on
Artificial Intelligence (EPIA 2001), LNAI 2258",
YEAR = 2001,
PAGES = "63--73",
PUBLISHER = "Springer",
MONTH = "December")
Citations (may not include all citations):357 Approximation by superpositions of a sigmoidal function (context) - Cybenko - 1987
237 A direct adaptive method for faster backpropagation learning.. - Riedmiller, Braun - 1993
227 An introduction to computing with neural nets (context) - Lippmann - 1987
221 Perceptrons: Introduction to Computational Geometry (context) - Minsky, Papert - 1988
214 Universal approximation bounds for superpositions of a sigmo.. (context) - Barron - 1993
120 Designing neural networks using genetic algorithms (context) - Miller, Todd et al. - 1989
31 SNNS Stuttgart Neural Network Simulator - Zell, Mamier et al. - 1994
15 Learning and approximation capabilities of adaptive spline a.. - Vecci, Piazza et al. - 1998
3 The Foundational Theory of Optimal Bayesian Pairwise Linear .. (context) - Rueda, Oommen - 2000
3 Neural networks with periodic and monotonic activation funct.. (context) - Sopena, Romero et al. - 1999
2 Evolutionary Design of Arti cial Neural Networks with Di ere.. (context) - Liu, Yao - 1996
2 Carnegie Mellon University (context) - ftp, cs et al. - 1993
Documents on the same site (http://www.cosy.sbg.ac.at/project/sigis/Papers/): More
ERC - Evolutionary Resample and Combine for Adaptive Parallel.. - Huber, Mayer (1998) (Correct)
Symbiotic Coevolution of Artificial Neural Networks and Training.. - Mayer (1998) (Correct)
Differentiation of Neuron Types by Evolving Activation.. - Mayer, Schwaiger (2002) (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