1) La descarga del recurso depende de la página de origen
2) Para poder descargar el recurso, es necesario ser usuario registrado en Universia


Opción 1: Descargar recurso

Detalles del recurso

Descripción

A Bayesian SOM (BSOM) [8], is proposed and applied to the unsupervised learning of Gaussian mixture distributions and its performance is compared with the expectation-maximisation (EM) algorithm. The BSOM is found to yield as good results as the well-known EM algorithm but with much fewer iterations and, more importantly it can be used as an on-line training method. The neighbourhood function and distance measures of the traditional SOM [3] are replaced by the neuron's on-line estimated posterior probabilities, which can be interpreted as a Bayesian inference of the neuron's opportunity to share in the winning response and so to adapt to the input pattern. Such posteriors starting from uniform priors are gradually sharpened when more and more data samples become available and so improve the estimation of model parameters. Each neuron then converges to one component of the mixture. Experimental results are compared with those of the EM algorithm.

Pertenece a

Faculty of Technology ePrints Service  

Autor(es)

Yin, Hujun -  Allinson, Nigel - 

Id.: 55198554

Versión: 1.0

Estado: Final

Tipo:  application/pdf - 

Palabras claveG400 Computer Science - 

Tipo de recurso: Conference or Workshop Item  -  PeerReviewed  - 

Tipo de Interactividad: Expositivo

Nivel de Interactividad: muy bajo

Audiencia: Estudiante  -  Profesor  -  Autor  - 

Estructura: Atomic

Coste: no

Copyright: sí

Formatos:  application/pdf - 

Requerimientos técnicos:  Browser: Any - 

Relación: [References] http://users.ics.tkk.fi/wsom97/program.html
[References] http://eprints.lincoln.ac.uk/5020/

Fecha de contribución: 13-oct-2012

Contacto:

Localización:
* Yin, Hujun and Allinson, Nigel (1997) Comparison of a Bayesian SOM with the EM algorithm for Gaussian mixtures. In: Workshop on Self-Organising Maps (WSOM'97), 4-6 June 1997, Helsinki, Finland.

Otros recursos del mismo autor(es)

  1. Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI Purpose: We propose a fully automated method for detection and segmentation of the abnormal tissue a...
  2. An experimental demonstration of a new type of proton computed tomography using a novel silicon tracking detector Radiography and tomography using proton beams promises benefit to image-guidance and treatment plann...
  3. One hundred engineering ideas that changed the world The above year-long exhibition organised by the Institution of Engineering and Technology for their...
  4. Method and apparatus for proton computed tomography A method of reconstructing a 3-dimensional image in a proton transmission computerised tomography (C...
  5. Assembly, apparatus, system and method (PRaVDA range telescope) Some embodiments of the present invention provide apparatus for detecting particles of radiation com...

Otros recursos de la mismacolección

  1. Evidence-based practice for nurses and healthcare professionals In the current healthcare climate, it is more important than ever to be able to select and find the ...
  2. The impossible fairytale or resistance to the real Whether they desire it or not, people with disabilities are frequently the objects of stares – yet t...
  3. Christoph Schlingensief: art without borders The work of acclaimed German artist Christoph Schlingensief spans three decades and a diverse range ...
  4. A campsite for the avant-garde and a church in cyberspace: Christoph Schlingensief’s dialogue with avant-gardism This essay examines Schlingensief’s reframing of the relationships between violence, terrorism and a...
  5. CI2 for creating and comparing confidence-intervals for time-series bivariate plots Currently no method exists for calculating and comparing the confidence-intervals (CI) for the time-...

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.