| 000 | 01166camuu2200337 a 4500 | |
| 001 | 000000643098 | |
| 005 | 19990916091658 | |
| 008 | 960517s1996 nyua b 001 0 eng | |
| 010 | ▼a 96022079 | |
| 015 | ▼a C97-3423-7 | |
| 020 | ▼a 0387947248 (softcover : alk. paper) | |
| 040 | ▼a DLC ▼c DLC ▼d FPU ▼d NLC | |
| 049 | ▼l 121041113 ▼f 과학 | |
| 050 | 0 0 | ▼a QA279.5 ▼b .N43 1996 |
| 055 | 0 1 | ▼a QA279.5 |
| 082 | 0 0 | ▼a 006.3 ▼2 20 |
| 090 | ▼a 006.3 ▼b N342b | |
| 100 | 1 | ▼a Neal, Radford M. |
| 245 | 1 0 | ▼a Bayesian learning for neural networks / ▼c Radford M. Neal. |
| 260 | ▼a New York : ▼b Springer, ▼c 1996. | |
| 300 | ▼a xi, 183 p. : ▼b ill. ; ▼c 24 cm. | |
| 490 | 1 | ▼a Lecture notes in statistics ; ▼v 118 |
| 504 | ▼a Includes bibliographical references and index. | |
| 650 | 0 | ▼a Bayesian statistical decision theory. |
| 650 | 0 | ▼a Machine learning. |
| 650 | 0 | ▼a Neural networks (Computer science) |
| 650 | 7 | ▼a Statistique bayesienne. ▼2 ram |
| 650 | 7 | ▼a Apprentissage automatique. ▼2 ram |
| 650 | 7 | ▼a Reseaux neuronaux (Informatique). ▼2 ram |
| 830 | 0 | ▼a Lecture notes in statistics (Springer-Verlag) ; ▼v v. 118. |
소장정보
| No. | 소장처 | 청구기호 | 등록번호 | 도서상태 | 반납예정일 | 예약 | 서비스 |
|---|---|---|---|---|---|---|---|
| No. 1 | 소장처 과학도서관/Sci-Info(2층서고)/ | 청구기호 006.3 N342b | 등록번호 121041113 (8회 대출) | 도서상태 대출가능 | 반납예정일 | 예약 | 서비스 |
컨텐츠정보
책소개
Artificial "neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional training methods. Insight into the nature of these complex Bayesian models is provided by a theoretical investigation of the priors over functions that underlie them. A practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods is also described, and software for it is freely available over the Internet. Presupposing only basic knowledge of probability and statistics, this book should be of interest to researchers in statistics, engineering, and artificial intelligence.
Artificial "neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional training methods. Insight into the nature of these complex Bayesian models is provided by a theoretical investigation of the priors over functions that underlie them. A practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods is also described, and software for it is freely available over the Internet. Presupposing only basic knowledge of probability and statistics, this book should be of interest to researchers in statistics, engineering, and artificial intelligence.
정보제공 :
목차
Preface; 1: Introduction; 2: Priors for Infinite Networks; 3: MonteCarlo Implementation; 4: Evaluation of Neural Network Models; 5:Conclusions and Further Work; A: Details of the Implementation; B:Obtaining the Software; Bibliography; Index
정보제공 :