Bayesian model comparison versus generalization ability of neural networks

被引：0

作者：

Gomari, M ^{[1
]}

Järvi, T ^{[1
]}

机构：

[1] Turku Ctr Comp Sci, FIN-20520 Turku, Finland

来源：

INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL I AND II | 1999年

关键词：

neural networks; classification; Bayesian inference; evidence; generalization;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Generalization ability is a desired feature for any model used for predicting new situation based on some previously learned knowledge. Often a neural network model with a good performance on the training cases does not provide an adequate performance for the unseen cases, i.e. the model is called to have a poor generalization ability. In this paper we discuss the applicability of the Bayesian techniques for measuring the generalization ability of neural networks through a medical case study.

引用

页码：537 / 541

页数：5

共 50 条

[31] An investigation on generalization ability of artificial neural networks and M5 model tree in modeling reference evapotranspiration
Kisi, Ozgur
Kilic, Yasin
THEORETICAL AND APPLIED CLIMATOLOGY, 2016, 126 (3-4) : 413 - 425
[32] An investigation on generalization ability of artificial neural networks and M5 model tree in modeling reference evapotranspiration
Ozgur Kisi
Yasin Kilic
Theoretical and Applied Climatology, 2016, 126 : 413 - 425
[33] Predicting the generalization ability of neural networks resembling the nearest-neighbor algorithm
Muselli, M
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL I, 2000, : 27 - 32
[34] Improving generalization ability of neural networks ensemble with multi-task learning
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China
不详
J. Comput. Inf. Syst., 2006, 4 (1235-1240):
[35] An Approach to Pruning the Structure of Convolutional Neural Networks without Loss of Generalization Ability
Chen, Chaoxiang
Kroshchanka, Aliaksandr
Golovko, Vladimir
Golovko, Olha
PATTERN RECOGNITION AND IMAGE ANALYSIS, 2024, 34 (02) : 258 - 265
[36] Generalization Comparison of Deep Neural Networks via Output Sensitivity
Forouzesh, Mahsa
Salehi, Farnood
Thiran, Patrick
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 7411 - 7418
[37] Regularization theory in the study of generalization ability of a biological neural network model
Aleksandra Świetlicka
Advances in Computational Mathematics, 2019, 45 : 1793 - 1805
[38] Regularization theory in the study of generalization ability of a biological neural network model
Swietlicka, Aleksandra
ADVANCES IN COMPUTATIONAL MATHEMATICS, 2019, 45 (04) : 1793 - 1805
[39] Travel Mode Choice Modeling: A Comparison of Bayesian Networks and Neural Networks
Tang, Dounan
Yang, Min
Zhang, Meihui
SUSTAINABLE CITIES DEVELOPMENT AND ENVIRONMENT, PTS 1-3, 2012, 209-211 : 717 - 723
[40] Identification versus generalization comment on the criticism of indeterminacy of artificial neural networks
Holena, Martin
APPLIED CATALYSIS A-GENERAL, 2008, 334 (1-2) : 381 - 385

← 1 2 3 4 5 →