Inequalities of generalization errors for layered neural networks in Bayesian learning

被引：0

作者：

Watanabe, S ^{[1
]}

机构：

[1] Tokyo Inst Technol, Precis & Intelligence Lab, Midori Ku, Yokohama, Kanagawa 2268503, Japan

来源：

ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3 | 1998年

关键词：

Bayesian learning; layered neural networks; generalization error;

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：

This paper proves inequalities of generalization errors for layered neural networks in Bayesian learning. It is shown that, if a three layer perceptron with M input units, H hidden units, and N output units is trained to learn the true model with H-1 hidden units, the generalization error is smaller than D/(2n) where D is the number of parameters and n is the number of training samples.

引用

页码：59 / 62

页数：4

共 50 条

[21] UNSUPERVISED DYNAMIC LEARNING IN LAYERED NEURAL NETWORKS
JONKER, HJJ
COOLEN, ACC
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1991, 24 (17): : 4219 - 4234
[22] Efficacy of Bayesian Neural Networks in Active Learning
Rakesh, Vineeth
Jain, Swayambhoo
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 2601 - 2609
[23] Continual Learning Using Bayesian Neural Networks
Li, Honglin
Barnaghi, Payam
Enshaeifare, Shirin
Ganz, Frieder
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (09) : 4243 - 4252
[24] Bayesian Nonparametric Federated Learning of Neural Networks
Yurochkin, Mikhail
Agarwal, Mayank
Ghosh, Soumya
Greenewald, Kristjan
Hoang, Trong Nghia
Khazaeni, Yasaman
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[25] Bayesian learning for neural networks: an algorithmic survey
Martin Magris
Alexandros Iosifidis
Artificial Intelligence Review, 2023, 56 : 11773 - 11823
[26] Variational Learning of Bayesian Neural Networks via Bayesian Dark Knowledge
Shen, Gehui
Chen, Xi
Deng, Zhihong
PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2037 - 2043
[27] LEARNING NEURAL NETWORKS WITH RESPECT TO TOLERANCES TO WEIGHT ERRORS
RUZICKA, P
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1993, 40 (05) : 331 - 342
[28] GENERALIZATION BY NEURAL NETWORKS
SHEKHAR, S
AMIN, MB
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1992, 4 (02) : 177 - 185
[29] On generalization by neural networks
Kak, SC
INFORMATION SCIENCES, 1998, 111 (1-4) : 293 - 302
[30] Committee neural network potentials control generalization errors and enable active learning
Schran, Christoph
Brezina, Krystof
Marsalek, Ondrej
JOURNAL OF CHEMICAL PHYSICS, 2020, 153 (10):

← 1 2 3 4 5 →