𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Learning Bayesian networks in the space of structures by estimation of distribution algorithms

✍ Scribed by Rosa Blanco; Iñaki Inza; Pedro Larrañaga

Publisher
John Wiley and Sons
Year
2003
Tongue
English
Weight
155 KB
Volume
18
Category
Article
ISSN
0884-8173

No coin nor oath required. For personal study only.

✦ Synopsis

The induction of the optimal Bayesian network structure is NP-hard, justifying the use of search heuristics. Two novel population-based stochastic search approaches, univariate marginal distribution algorithm (UMDA) and population-based incremental learning (PBIL), are used to learn a Bayesian network structure from a database of cases in a score ϩ search framework. A comparison with a genetic algorithm (GA) approach is performed using three different scores: penalized maximum likelihood, marginal likelihood, and information-theory-based entropy. Experimental results show the interesting capabilities of both novel approaches with respect to the score value and the number of generations needed to converge.

📜 SIMILAR VOLUMES

A method of BP network learning by expan
A method of BP network learning by expanding the distribution of category
✍ Naoki Tanaka; Toshiaki Koreyeda; Takeshi Inoue; Koji Kajitani 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 300 KB

In backpropagation networks, unlearned regions are left between categories if the learning samples are comparatively small. Such unlearned regions are one of the reasons for the degradation of network generalization ability. To improve the generalization ability, it is preferable that the boundaries

An application of Bayesian (ABIC) smooth
An application of Bayesian (ABIC) smoothing methods to estimating space and time variations in the magnitude distributions of earthquakes
✍ Masajiro Imoto 📂 Article 📅 1991 🏛 Springer Japan 🌐 English ⚖ 940 KB

On the basis of Akaike's Bayesian information criterion (ABIC), a new method of estimating temporal and spacial variations in the magnitudefrequency relation (b value) is developed. The space-time volume studied is divided into a number of segments having equal volume, for which b values are estimat