(Enter summary)
Abstract: Three Bayesian ideas are presented for supervised adaptive classifiers. First, it is
argued that the output of a classifier should be obtained by marginalising over the
posterior distribution of the parameters; a simple approximation to this integral is
proposed and demonstrated. This involves a `moderation' of the most probable classifier
's outputs, and yields improved performance. Second, it is demonstrated that the
Bayesian framework for model comparison described for regression models in... (Update)
Cited by: More
Faculteit Economie - En Bedrijfskunde Hoveniersberg
(Correct)
Active Learning for Logistic Regression - Schein (2005)
(Correct)
NOVELTY DETECTION BASED ON SPECTRAL SIMILARITY OF SONGS.. - Elias Pampalk Gerhard
(Correct)
Similar documents (at the sentence level):
64.6%: Bayesian Methods for Adaptive Models - MacKay (1992)
(Correct)
Active bibliography (related documents): More All
0.1: Information-Based Objective Functions for Active Data Selection - David J.C. MacKay
(Correct)
0.1: Active Learning for Function Approximation - Sung, Niyogi (1995)
(Correct)
0.1: Neural Networks: A Pattern Recognition Perspective - Bishop (1996)
(Correct)
Similar documents based on text: More All
0.2: Bayesian Model Comparison and Backprop Nets - David Mackay Computation (1992)
(Correct)
0.1: Responding to cognitive overload: Co-adaptation between users and .. - Mackay (2000)
(Correct)
0.1: Comparison of Approximate Methods for Handling Hyperparameters - MacKay
(Correct)
Related documents from co-citation: More All
29: Neural Networks for Pattern Recognition (context) - Bishop - 1995
27: Bayesian interpolation
- MacKay - 1992
25: Bayesian learning for neural networks (context) - Neal - 1995
BibTeX entry: (Update)
MacKay, D. J. C. 1992a. The evidence framework applied to classification networks. Neural Computation 4. http://citeseer.ist.psu.edu/mackay92evidence.html More
@article{ mackay92evidence,
author = "MacKay, D.",
title = "The Evidence Framework Applied to Classification Networks",
journal = "Neural Computation",
volume = "4",
number = "5",
pages = "720--736",
year = "1992",
url = "citeseer.ist.psu.edu/mackay92evidence.html" }
Citations (may not include all citations):
138
Learning and relearning in Boltzmann machines (context) - Hinton, Sejnowski - 1986
130
Probabilistic interpretation of feedforward classification n.. (context) - Bridle - 1989
118
Sequential updating of conditional probabilities on directed.. (context) - Spiegelhalter, Lauritzen - 1990
58
Statistical mechanics of learning from examples (context) - Seung, Sompolinsky et al. - 1991
43
Neural net algorithms that learn in polynomial time from exa.. (context) - Baum - 1991
40
Bayesian methods for adaptive models
- MacKay - 1991 ACM
39
Accelerated learning in layered neural networks (context) - Solla, Levin et al. - 1988 ACM
32
Query--based learning applied to partially trained multilaye.. (context) - Hwang, Choi et al. - 1991
29
Exact calculation of the Hessian matrix for the multilayer p.. (context) - Bishop - 1992 ACM
18
Learning algorithms and probability distributions in feed--f.. (context) - Hopfield - 1987
9
Active selection of training examples for network learning i.. (context) - Plutowski, White - 1991
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://wol.ra.phy.cam.ac.uk/pub/mackay/README.html): More
Variational Gaussian Process Classifiers - Gibbs, MacKay (1997)
(Correct)
Neural Network Image Deconvolution - Tansley, Oldfield, MacKay (1996)
(Correct)
Ensemble Learning and Evidence Maximization - MacKay (1995)
(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