|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
An Introduction to Sum Product Networks
If you have a question about this talk, please contact Colorado Reed.
Sum product networks (SPNs) are a new family of deep probabilistic models in which exact inference is tractable. SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges. A SPN is an arithmetic circuit which under some conditions (completeness and consistency) represents the partition function and all marginals of some graphical model. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also more general. Discriminative and generative learning of SPNs can be efficiently implemented using hard EM and hard gradient descent. These methods avoid the problem of gradient diffusion in deep architectures and allow us to effectively work with SPNs of more than 30 layers of hidden variables. Several experiments show that SPNs have state of the art performance on different image completion and classification tasks, outperforming alternative deep and shallow methods.
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsPragmatics reading group Inference Group Journal Clubs CU Labour Club: All Events
Other talksIrish barding poetry, c.1600 Patterns of medical practice in urban and rural England, c.1500–1720: a case-study of the South West MEMS Biosensors and their potential for improving healthcare Jane Squire's early modern adventures: 'I see not why I should confine myself to needles, cards, and dice' Children's Literature & Dress: Narration, Characterisation, Reception Contributed Talk 5: Numerical Continuation of Equilibria of Cell Population Models with Internal Cell Cycle