Bayesian Learning for Neural Networks (häftad)
Format
Häftad (Paperback)
Språk
Engelska
Antal sidor
204
Utgivningsdatum
1996-08-01
Upplaga
1996.
Förlag
Springer-Verlag New York Inc.
Illustrationer
biography
Dimensioner
221 x 150 x 13 mm
Vikt
318 g
Antal komponenter
1
Komponenter
Paperback
ISBN
9780387947242

Bayesian Learning for Neural Networks

Häftad, Engelska, 1996-08-01
1751 kr
Skickas inom 2-5 vardagar.
Fri frakt inom Sverige för privatpersoner.
Finns även som
Visa alla 1 format & utgåvor
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.
Visa hela texten

Passar bra ihop

  1. Bayesian Learning for Neural Networks
  2. +
  3. Sapiens

De som köpt den här boken har ofta också köpt Sapiens av Yuval Noah Harari (häftad).

Köp båda 2 för 1864 kr

Kundrecensioner

Har du läst boken? Sätt ditt betyg »

Bloggat om Bayesian Learning for Neural Networks

Innehållsförteckning

Preface; 1: Introduction; 2: Priors for Infinite Networks; 3: Monte Carlo Implementation; 4: Evaluation of Neural Network Models; 5: Conclusions and Further Work; A: Details of the Implementation; B: Obtaining the Software; Bibliography; Index