Access the full text.
Sign up today, get DeepDyve free for 14 days.
W. Dearborn (1910)
Experiments in learning.Journal of Educational Psychology, 1
R. Fletcher (1987)
Practical methods of optimization; (2nd ed.)
J. Denker, D. Schwartz, Ben Wittner, S. Solla, R. Howard, L. Jackel, J. Hopfield (1987)
Large Automatic Learning, Rule Extraction, and GeneralizationComplex Syst., 1
P. Williams (1993)
Improved generalization and network pruning using adaptive Laplace regularization
D. Plaut, S. Nowlan, Geoffrey Hinton (1986)
Experiments on Learning by Back Propagation.
D. Signorini, J. Slattery, S. Dodds, V. Lane, P. Littlejohns (1995)
Neural networksThe Lancet, 346
H. Thodberg (1993)
Ace of Bayes : Application of Neural
P. Williams (1996)
Using Neural Networks to Model Conditional Multivariate DensitiesNeural Computation, 8
D. MacKay (1992)
A Practical Bayesian Framework for Backpropagation NetworksNeural Computation, 4
C. Bishop (1992)
Curvature-Driven Smoothing in Backpropagation Neural Networks
D. MacKay (1991)
A Practical Bayesian Framework for Backprop NetworksNeural Computation
Radford Neal (1992)
Bayesian Learning via Stochastic Dynamics
R. Fletcher (1988)
Practical Methods of Optimization
(1991)
A Marquardt algorithm for choosing the step-size
P. Gill, W. Murray, M. Wright (2019)
Practical optimization
Yann LeCun, J. Denker, S. Solla (1989)
Optimal Brain Damage
A. Tikhonov, Vasiliy Arsenin (1977)
Solutions of ill-posed problems
T. Johansen (1996)
Identification of non-linear systems using empirical data and prior knowledge - an optimization approachAutom., 32
Charles Bishop (1993)
Curvature-driven smoothing: a learning algorithm for feedforward networksIEEE transactions on neural networks, 4 5
M. Møller (1993)
Exact Calculation of the Product of the Hessian Matrix of Feed-Forward Network Error Functions and a Vector in 0(N) Time, 22
D. Wolpert (1992)
On the Use of Evidence in Neural Networks
(1991)
AMarquardt algorithm for choosing the step-size in backpropagation learning with conjugate gradients
A. Weigend, D. Rumelhart, B. Huberman (1990)
Generalization by Weight-Elimination with Application to Forecasting
M. Møller (1990)
A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning, 19
Barak Pearlmutter (1994)
Fast Exact Multiplication by the HessianNeural Computation, 6
D. MacKay (1992)
Bayesian InterpolationNeural Computation, 4
(1994)
Hyperparameters: Optimise, or integrate out? In Maxiiriuin Eiitropy arid Bayesian Methods, Sarita Barbnra, 1993, G
Radford Neal (1992)
Bayesian training of backpropagation networks by the hybrid Monte-Carlo method
E. Jaynes (1968)
Prior Probabilities
B. Hassibi, D. Stork (1992)
Second Order Derivatives for Network Pruning: Optimal Brain Surgeon
Wray Buntine, A. Weigend (1991)
Bayesian Back-PropagationComplex Syst., 5
S. Nowlan, Geoffrey Hinton (1991)
Adaptive Soft Weight Tying using Gaussian Mixtures
Standard techniques for improved generalization from neural networks include weight decay and pruning. Weight decay has a Bayesian interpretation with the decay function corresponding to a prior over weights. The method of transformation groups and maximum entropy suggests a Laplace rather than a gaussian prior. After training, the weights then arrange themselves into two classes: (1) those with a common sensitivity to the data error and (2) those failing to achieve this sensitivity and that therefore vanish. Since the critical value is determined adaptively during training, pruning—in the sense of setting weights to exact zeros—becomes an automatic consequence of regularization alone. The count of free parameters is also reduced automatically as weights are pruned. A comparison is made with results of MacKay using the evidence framework and a gaussian regularizer.
Neural Computation – MIT Press
Published: Jan 1, 1995
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.