Recurrent sampling models.
In: Wong, KYM and King, I and Yeung, DY, (eds.)
THEORETICAL ASPECTS OF NEURAL COMPUTATION.
(pp. 287 - 296).
SPRINGER-VERLAG SINGAPORE PTE LTD
Hierarchical probabilistic synthesis and analysis models have recently been suggested as architectures for performing density estimation. Strict hierarchies makes it easy to evaluate generative or synthetic probabilities. However, both theoretical and neurobiological considerations weigh in favour of integrating lateral influences within a layer together with top-down and bottom up influences from lower and higher layers. This is known to be computationally tricky. We suggest a new recurrent sampling model and show that has the appropriate structure and behaviour for the analysis model for linear and Gaussian factor analysis. Then we extend this model to the case of binary stochastic units. Finally, we comment on the more general use of this model.
|Title:||Recurrent sampling models|
|Event:||Hong Kong International Workshop on Theoretical Aspects of Neural Computation - A Multi-Disciplinary Perspective (TANC-97)|
|Location:||HONG KONG UNIV SCI & TECHNOL, CLEARWATER BAY, HONG KONG|
|Dates:||1997-05-26 - 1997-05-28|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only