Neil D. Lawrence  Home/Search
Context Related
| thelawrences.net/neil/ltupaper.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: thelawrences.net/n...publications (more) Homepages: N.Lawrence |
Rate this article:      (best)Comment on this article |
Abstract: Linear threshold units (LTUs) were originally proposed as models of biological neurons. They were widely studied in the context of the perceptron (Rosenblatt, 1962). Due to the diculties of nding a general algorithm for networks with hidden nodes, they never passed into general use. In this work we derive an algorithm in the context of a probabilistic models and show how it may be applied in multi-layer networks of linear threshold units. We demonstrate the performance of the algorithm on three ... (Update)
Context of citations to this paper: More
.... mention some heuristics which were found useful in the practical implementation of the algorithm, further details may also be found in Lawrence, 2000. 5.1.1 Simulated annealing The updates of Eqn 18 are taking place in a highly discontinuous space. It may be advantageous to...
Cited by: More
Variational Learning for Multi-Layer Networks of Linear.. - Lawrence (2001) (Correct)
Active bibliography (related documents): More All
0.4: Tutorial on Variational Approximation Methods - Jaakkola (2000) (Correct)
0.3: Maximum Entropy Discrimination - Jaakkola, Meila, Jebara (1999) (Correct)
0.3: Model-Independent Mean Field Theory as a Local Method for.. - Haft, Hofmann, Tresp (2002) (Correct)
Similar documents based on text: More All
0.4: The Structure of Bayesian Neural Network Posteriors - Lawrence, Azzouzi (Correct)
0.3: A Dynamical Study of the Generalised Delta Rule - Butler (2000) (Correct)
0.1: On the Power of Democratic Networks - Eddy Mayoraz (1996) (Correct)
BibTeX entry: (Update)
Lawrence, N. D. (2000). Variational learning in multilayer networks of linear threshold units. Draft report. http://citeseer.ist.psu.edu/lawrence01variational.html More
@misc{ lawrence00variational,
author = "N. Lawrence",
title = "Variational learning in multilayer networks of linear threshold units",
text = "Lawrence, N. D. (2000). Variational learning in multilayer networks of
linear threshold units. Draft report.",
year = "2000",
url = "citeseer.ist.psu.edu/lawrence01variational.html" }
Citations (may not include all citations):2528 Maximum likelihood from incomplete data via the EM algorithm (context) - Dempster, Laird et al. - 1977
1662 Neural Networks for Pattern Recognition (context) - Bishop - 1995
490 Pattern Recognition and Neural Networks - Ripley - 1996
431 A tutorial on support vector machines for pattern recognitio.. - Burges - 1998
348 Estimation of Dependences Based on Empirical Data (context) - Vapnik - 1982
191 Fast training of support vector machines using sequential mi.. (context) - Platt - 1998
111 Connectionist learning of belief networks (context) - Neal - 1992
102 Principles of Neurodynamics: Perceptrons and the Theory of B.. (context) - Rosenblatt - 1962
102 Neurocomputing: Foundations of Research (context) - Anderson, Rosenfeld - 1988
63 Keeping neural networks simple by minimizing the description.. - Hinton, van Camp - 1993
22 Developments in probabilistic modelling with neural networks.. - MacKay - 1995
17 Mean eld theory for sigmoid belief networks (context) - Saul, Jaakkola et al. - 1996
7 Gaussian processes for Bayesian classication via hybrid Mont.. (context) - Barber, Williams - 1997
5 Flexible non-linear approaches to classication (context) - Ripley - 1994
3 Model-independent mean eld theory as a local method for appr.. (context) - Haft, Ho et al. - 1999
2 A comparison of state-of-the-art classi cation techniques wi.. (context) - Lerner, Lawrence - 1999
Documents on the same site (http://www.thelawrences.net/neil/publications.html): More
A Comparison of State-of-the-Art Classification Techniques.. - Lerner, Lawrence (2001) (Correct)
Optimising Synchronisation Times for Mobile Devices - Lawrence, Rowstron, Bishop.. (2001) (Correct)
Fast Sparse Gaussian Process Methods: The Informative.. - Lawrence, Seeger.. (2003) (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