Hinton, GE and Ghahramani, Z and Teh, YW (2000) Learning to parse images. In: Solla, SA and Leen, TK and Muller, KR, (eds.) ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 12. (pp. 463 - 469). M I T PRESS
Full text not available from this repository.
We describe a class of probabilistic models that we call credibility networks. Using parse trees as internal representations of images, credibility networks are able to perform segmentation and recognition simultaneously, removing the need for ad hoc segmentation heuristics. Promising results in the problem of segmenting handwritten digits were obtained.
|Title:||Learning to parse images|
|Event:||13th Annual Conference on Neural Information Processing Systems (NIPS)|
|Dates:||1999-11-29 - 1999-12-04|
|Keywords:||LIKELIHOOD, ALGORITHM, NETWORKS|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only: edit this record