Download:
|
by Michael E. Rimer, Tony R. Martinez, D. Randall Wilson
ftp://axon.cs.byu.edu/pub/papers/rimer.ijcnn02.ps
Add To MetaCart
Abstract:
randy @ axon. cs. byu. edu Abstract- Backpropagation, like most high-order learning algorithms, is prone to overfitting. We present a novel approach, called lazy training, for reducing the overfit in multiple-output networks. Lazy training has been shown to reduce the error of optimized neural networks by more than half on a large OCR data set and on several problems from the UCI machine learning database. Here, lazy training is shown to be effective in a multi-layered adaptive learning system, reducing the error of an optimized backpropagation network in a speech recognition system by 55.0 % on the TIDIGITS corpus.
Citations
|
2140
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
2138
|
UCI Repository of Machine Learning Databases
– Merz, Murphy
- 1996
|
|
880
|
and B-H Juang, Fundamentals of Speech Recognition
– Rabiner
- 1993
|
|
129
|
The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network
– Bartlett
- 1998
|
|
84
|
An empirical evaluation of bagging and boosting
– Maclin, Opitz
- 1997
|
|
56
|
Optimization of the Backpropagation Algorithm for Training Multilayer Perceptrons, Fachbrericht Physik
– Schiffman, Joost, et al.
|
|
35
|
Comparison of optimized backpropagation algorithms
– Schiffmann, Joost, et al.
- 1993
|
|
27
|
Backpropagation: Past and future
– Werbos
- 1988
|
|
26
|
Connected Letter Recognition with a Multi-State Time Delay Neural Network
– Hild, Waibel
- 1993
|
|
22
|
An iterative pruning algorithm for feedforward neural networks
– Castellano, Fanelli, et al.
- 1997
|
|
17
|
Optimal stopping and effective machine complexity in learning
– Wang, Venkatesh, et al.
- 1994
|
|
7
|
Performance and generalization of the classification figure of merit criterion function
– Barnard
- 1991
|
|
3
|
Improving Backpropagation Ensembles through Lazy Training
– Rimer, Anderson, et al.
- 2001
|
|
2
|
Cross Validation and MLP Architecture Selection
– Andersen, Martinez
- 1999
|
|
2
|
Wagging: A learning approach which allows single layer perceptrons to outperform more complex learning algorithms
– Andersen, Martinez
- 1999
|
|
2
|
TI_DIGITS speech corpus
– Leonard, Doddington
- 1993
|
|
1
|
An empirical comparison of node pruning methods for layered feed-forward neural networks
– Castellano, Fanelli, et al.
- 1993
|
|
1
|
A Novel Objective Function for Improved Phoneme Recognition Using Time-Delay Neural Networks
– 1I, John
- 1990
|
