Equivalent number of degrees of freedom for neural networks

被引：5

作者：

Ingrassia, Salvatore ^{[1
]}

Morlin, Isabella ^{[2
]}

机构：

[1] Univ Catania, Dipartimento Economia Metodi Quantitativi, Corso Italia 55, I-95128 Catania, Italy

[2] Univ Modena, Dept Social Cognit & Quantat, Reggio Emilia, Italy

来源：

ADVANCES IN DATA ANALYSIS | 2007年

关键词：

D O I：

10.1007/978-3-540-70981-7_26

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The notion of equivalent number of degrees of freedom (e.d.f.) to be used in neural network modeling from small datasets has been introduced in Ingrassia and Morlini (2005). It is much smaller than the total number of parameters and it does not depend on the number of input variables. We generalize our previous results and discuss the use of the e.d.f. in the general framework of multivariate nonparametric model selection. Through numerical simulations, we also investigate the behavior of model selection criteria like AIC, GCV and BIC/SBC, when the e.d.f. is used instead of the total number of the adaptive parameters in the model.

引用

页码：229 / +

页数：2

共 50 条

[1] NUMBER OF DEGREES OF FREEDOM, CORRELATION TIMES, AND EQUIVALENT BANDWIDTHS OF A RANDOM PROCESS
KIKKAWA, S
ISHIDA, M
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 1988, 34 (01) : 151 - 155
[2] COMPUTATIONAL STUDIES WITH EQUIVALENT DEGREES OF FREEDOMS IN NEURAL NETWORKS
Ingrassia, Salvatore
Morlini, Isabella
[J]. ADVANCES AND APPLICATIONS IN STATISTICS, 2009, 13 (01) : 49 - 81
[3] NUMBER OF DEGREES OF FREEDOM FOR A THERMOSTAT
KOLOVSKY, AR
[J]. PHYSICAL REVIEW E, 1994, 50 (05) : 3569 - 3576
[4] Exploiting optical degrees of freedom for information multiplexing in diffractive neural networks
Chao Zuo
Qian Chen
[J]. Light: Science & Applications, 11
[5] Exploiting optical degrees of freedom for information multiplexing in diffractive neural networks
Zuo, Chao
Chen, Qian
[J]. Light: Science and Applications, 2022, 11 (01):
[6] Exploiting optical degrees of freedom for information multiplexing in diffractive neural networks
Zuo, Chao
Chen, Qian
[J]. LIGHT-SCIENCE & APPLICATIONS, 2022, 11 (01)
[7] On the representer theorem and equivalent degrees of freedom of SVR
Dinuzzo, Francesco
Neve, Marta
De Nicolao, Giuseppe
Gianazza, Ugo Pietro
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2007, 8 : 2467 - 2495
[8] On the number of degrees of freedom in biological limbs
Gielen, S
van Bolhuis, B
Vrijenhoek, E
[J]. PROGRESS IN MOTOR CONTROL, VOL 1: BERNSTEINS TRADITIONS IN MOVEMENT STUDIES, 1998, : 173 - 190
[9] An alternative to the effective number of degrees of freedom
Alex Williams
[J]. Accreditation and Quality Assurance, 1999, 4 : 14 - 17
[10] NUMBER OF DEGREES OF FREEDOM IN INVERSE DIFFRACTION
BERTERO, M
DEMOL, C
GORI, F
RONCHI, L
[J]. OPTICA ACTA, 1983, 30 (08): : 1051 - 1065

← 1 2 3 4 5 →