Early stopping by correlating online indicators in neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ferro, Manuel Vilares, Mosquera, Yerai Doval, Pena, Francisco J. Ribadas, Bilbao, Victor M. Darriba
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914666367680512
author Ferro, Manuel Vilares
Mosquera, Yerai Doval
Pena, Francisco J. Ribadas
Bilbao, Victor M. Darriba
author_facet Ferro, Manuel Vilares
Mosquera, Yerai Doval
Pena, Francisco J. Ribadas
Bilbao, Victor M. Darriba
contents In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables support of a reliable and trustworthy early stopping condition, thus improving the predictive power of that type of modeling. Our proposal exploits the correlation over time in a collection of online indicators, namely characteristic functions for indicating if a set of hypotheses are met, associated with a range of independent stopping conditions built from a canary judgment to evaluate the presence of overfitting. That way, we provide a formal basis for decision making in terms of interrupting the learning process. As opposed to previous approaches focused on a single criterion, we take advantage of subsidiarities between independent assessments, thus seeking both a wider operating range and greater diagnostic reliability. With a view to illustrating the effectiveness of the halting condition described, we choose to work in the sphere of natural language processing, an operational continuum increasingly based on machine learning. As a case study, we focus on parser generation, one of the most demanding and complex tasks in the domain. The selection of cross-validation as a canary function enables an actual comparison with the most representative early stopping conditions based on overfitting identification, pointing to a promising start toward an optimal bias and variance control.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02513
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Early stopping by correlating online indicators in neural networks
Ferro, Manuel Vilares
Mosquera, Yerai Doval
Pena, Francisco J. Ribadas
Bilbao, Victor M. Darriba
Machine Learning
Artificial Intelligence
Computation and Language
Neural and Evolutionary Computing
In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables support of a reliable and trustworthy early stopping condition, thus improving the predictive power of that type of modeling. Our proposal exploits the correlation over time in a collection of online indicators, namely characteristic functions for indicating if a set of hypotheses are met, associated with a range of independent stopping conditions built from a canary judgment to evaluate the presence of overfitting. That way, we provide a formal basis for decision making in terms of interrupting the learning process. As opposed to previous approaches focused on a single criterion, we take advantage of subsidiarities between independent assessments, thus seeking both a wider operating range and greater diagnostic reliability. With a view to illustrating the effectiveness of the halting condition described, we choose to work in the sphere of natural language processing, an operational continuum increasingly based on machine learning. As a case study, we focus on parser generation, one of the most demanding and complex tasks in the domain. The selection of cross-validation as a canary function enables an actual comparison with the most representative early stopping conditions based on overfitting identification, pointing to a promising start toward an optimal bias and variance control.
title Early stopping by correlating online indicators in neural networks
topic Machine Learning
Artificial Intelligence
Computation and Language
Neural and Evolutionary Computing
url https://arxiv.org/abs/2402.02513