Similarities of error regularization, sigmoid gain scaling, target smoothing, and training with jitter

The generalization performance of feedforward layered perceptrons can, in many cases, be improved either by smoothing the target via convolution, regularizing the training error with a smoothing constraint, decreasing the gain (i.e., slope) of the sigmoid nonlinearities, or adding noise (i.e., jitte...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks 1995-05, Vol.6 (3), p.529-538
Main Authors: Reed, R., Marks, R.J., Oh, S.
Format: Article
Language:English
Subjects:
Applied sciences
Convolution
Costs
Electric, optical and optoelectronic circuits
Electronics
Exact sciences and technology
Jitter
Lagrangian functions
Neural networks
Noise cancellation
Performance gain
Probability density function
Sampling methods
Smoothing methods
Training data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The generalization performance of feedforward layered perceptrons can, in many cases, be improved either by smoothing the target via convolution, regularizing the training error with a smoothing constraint, decreasing the gain (i.e., slope) of the sigmoid nonlinearities, or adding noise (i.e., jitter) to the input training data, In certain important cases, the results of these procedures yield highly similar results although at different costs. Training with jitter, for example, requires significantly more computation than sigmoid scaling.< >
ISSN:1045-9227
1941-0093
DOI:10.1109/72.377960