Michael Schmitt  Home/Search
Context Related
| ruhrunibochum.de...erperceptron.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: ruhrunibochum.de/lmi/ms...index (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We investigate the computational complexity of identifying neural weights using Perceptron -like learning rules. These are understood as instructions to change weights by a fixed amount after occurrence of an error. (Update)
Context of citations to this paper: More
...W has the smallest size possible. In fact it can be shown that learning time must grow at least as jW j 2 = d 1) Lewis II, 1966; Schmitt, 1996). Again this is dominated by the jW j 2 term. Since both the upper and lower bounds grow as approximately jW j 2 , actual...
Cited by: More
Minimum Generalization via Reflection: A Fast Linear.. - Hampson, Kibler (1998) (Correct)
Similar documents (at the sentence level):
18.9%: Identification Criteria and Lower Bounds for Perceptron-like.. - Schmitt (1998) (Correct)
Active bibliography (related documents): More All
0.5: Boolean Functions and Artificial Neural Networks - Martin Anthony Department (Correct)
0.3: Décomposition Fonctionnelle Neuromimtique De.. - Breton, Gresser.. (1997) (Correct)
0.3: The Forbidden Projections of Unate Functions - Feigelson, Hellerstein (1997) (Correct)
Similar documents based on text: More All
0.3: On Methods to Keep Learning Away from Intractability (Extended.. - Schmitt (1995) (Correct)
0.3: A Fuzzy Medical Data Model - Steimann, Adlassnig (1994) (Correct)
0.2: On Computing Boolean Functions by a Spiking Neuron - Schmitt (1998) (Correct)
BibTeX entry: (Update)
Schmitt M., (1996) Lower Bounds on Identification Criteria for Perceptron-like Learning Rules. In: Proceedings of the thirteenth European meeting on cybernetics and systems research. EMCSR'96 2, 1049--1054, Ed. Trappi, R., Vienna. http://citeseer.ist.psu.edu/schmitt96lower.html More
@misc{ schmitt96lower,
author = "M. Schmitt",
title = "Lower Bounds on Identification Criteria for Perceptron-like Learning Rules",
text = "Schmitt M., (1996) Lower Bounds on Identification Criteria for Perceptron-like
Learning Rules. In: Proceedings of the thirteenth European meeting on cybernetics
and systems research. EMCSR'96 2, 1049--1054, Ed. Trappi, R., Vienna.",
year = "1996",
url = "citeseer.ist.psu.edu/schmitt96lower.html" }
Citations (may not include all citations):493 Communications of the ACM (context) - Valiant, of et al. - 1984
465 Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
441 Queries and concept learning (context) - Angluin - 1988
221 Perceptrons: An Introduction to Computational Geometry (context) - Minsky, Papert - 1988
148 The Perceptron: A probabilistic model for information storag.. (context) - Rosenblatt - 1958
144 Computational limitations on learning from examples (context) - Pitt, Valiant - 1988
102 Principles of Neurodynamics: Perceptrons and the Theory of B.. (context) - Rosenblatt - 1962
101 Threshold Logic and Its Applications (context) - Muroga - 1971
32 the size of weights for threshold gates - Hastad - 1994
26 How fast can a threshold gate learn (context) - Maass, Tur'an - 1994
22 On convergence proofs for Perceptrons (context) - Novikoff - 1962
20 Linear function neurons: Structure and training (context) - Hampson, Volper - 1986
19 Perspectives of current research about the complexity of lea.. - Maass - 1994
14 On exact specification by examples (context) - Anthony, Brightwell et al. - 1992
9 A logical calculus of the ideas immanent in nervous activity (context) - McCulloch, Pitts - 1943
7 Investigating the distribution assumptions in the pac learni.. (context) - Bartlett, Williamson - 1991
6 IEEE Transactions on Neural Networks (context) - Nagy, now - 1991
3 IRE Transactions on Electronic Computers (context) - McNaughton, functions - 1961
2 the size of weights for McCulloch-Pitts neurons - Schmitt - 1994
2 Foundations of Computing Series (context) - Parberry, Neural - 1994
2 Boolean functions realizable with single threshold devices (context) - Paull, McCluskey - 1960
Documents on the same site (http://www.ruhr-uni-bochum.de/lmi/mschmitt/index.html): More
On the Complexity of Consistency Problems for Neurons with Binary .. - Schmitt (1994) (Correct)
On the Complexity of Learning for Spiking Neurons with.. - Maass, Schmitt (1997) (Correct)
VC Dimension Bounds for Networks of Spiking Neurons - Schmitt (1999) (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