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

[41] Learning Structured Weight Uncertainty in Bayesian Neural Networks
Sun, Shengyang
Chen, Changyou
Carin, Lawrence
ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54, 2017, 54 : 1283 - 1292
[42] Random Feature Amplification: Feature Learning and Generalization in Neural Networks
Frei, Spencer
Chatterji, Niladri S.
Bartlett, Peter L.
JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
[43] Deferring the learning for better generalization in radial basis neural networks
Valls, JM
Isasi, P
Galván, IM
ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 189 - 195
[44] Learning errors by radial basis function neural networks and regularization networks
Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod vodárenskou věžíí 2, Prague 8, Czech Republic
Int. J. Grid Distrib. Comput., 2009, 1 (49-58):
[45] BIDIRECTIONAL HIERARCHICAL NEURAL NETWORKS Hebbian Learning Improves Generalization
Saifullah, Mohammad
Kovordanyi, Rita
Roy, Chandan
VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2010, : 105 - 111
[46] Learning Global Pairwise Interactions with Bayesian Neural Networks
Cui, Tianyu
Marttinen, Pekka
Kaski, Samuel
ECAI 2020: 24TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, 325 : 1087 - 1094
[47] Hierarchical Bayesian Inference and Learning in Spiking Neural Networks
Guo, Shangqi
Yu, Zhaofei
Deng, Fei
Hu, Xiaolin
Chen, Feng
IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (01) : 133 - 145
[48] Bayesian continual learning via spiking neural networks
Skatchkovsky, Nicolas
Jang, Hyeryung
Simeone, Osvaldo
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2022, 16
[49] Learning efficiency of redundant neural networks in Bayesian estimation
Watanabe, S
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06): : 1475 - 1486
[50] Asymptotics of representation learning in finite Bayesian neural networks*
Zavatone-Veth, Jacob A.
Canatar, Abdulkadir
Ruben, Benjamin S.
Pehlevan, Cengiz
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2022, 2022 (11):

← 1 2 3 4 5 →