Scaling Up Graphical Model Inference View observed

min-jolicoeur
Published  · 15 slides · 0 views
↓ Download
Scaling Up Graphical Model Inference View observed
1 / 1
Scaling Up Graphical Model Inference View observed - slide 1 of 15 Scaling Up Graphical Model Inference View observed - slide 2 of 15 Scaling Up Graphical Model Inference View observed - slide 3 of 15 Scaling Up Graphical Model Inference View observed - slide 4 of 15 Scaling Up Graphical Model Inference View observed - slide 5 of 15 Scaling Up Graphical Model Inference View observed - slide 6 of 15 Scaling Up Graphical Model Inference View observed - slide 7 of 15 Scaling Up Graphical Model Inference View observed - slide 8 of 15 Scaling Up Graphical Model Inference View observed - slide 9 of 15 Scaling Up Graphical Model Inference View observed - slide 10 of 15 Scaling Up Graphical Model Inference View observed - slide 11 of 15 Scaling Up Graphical Model Inference View observed - slide 12 of 15 Scaling Up Graphical Model Inference View observed - slide 13 of 15 Scaling Up Graphical Model Inference View observed - slide 14 of 15 Scaling Up Graphical Model Inference View observed - slide 15 of 15
Description
Scaling Up Graphical Model Inference View observed data and unobserved properties as random variables Graphical Models: compact graph-based encoding of probability distributions (high dimensional, with complex dependencies)

Related Topics

Download this presentation From Below

"Scaling Up Graphical Model Inference View observed" is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Presentation Transcript

01
Scaling Up Graphical Model Inference<br>
02
View observed data and unobserved properties as random variables
Graphical Models: compact graph-based encoding of probability distributions (high dimensional, with complex dependencies)




Generative/discriminative/hybrid, un-,semi- and supervised learning
Bayesian Networks (directed), Markov Random Fields (undirected), hybrids, extensions, etc. HMM, CRF, RBM, M3N, HMRF, etc.
Enormous research area with a number of excellent tutorials
[J98], [M01], [M04], [W08], [KF10], [S11] Graphical Models<br>
03
Graphical Model Inference Key issues:
Representation: syntax and semantics (directed/undirected,variables/factors,..)
Inference: computing probabilities and most likely assignments/explanations
Learning: of model parameters based on observed data. Relies on inference!
Inference is NP-hard (numerous results, incl. approximation hardness)
Exact inference: works for very limited subset of models/structures
E.g., chains or low-treewidth trees
Approximate inference: highly computationally intensive
Deterministic: variational, loopy belief propagation, expectation propagation
Numerical sampling (Monte Carlo): Gibbs sampling<br>