Abstract | ||
---|---|---|
We describe a method for learning Lie, or continuous transformation, group
descriptions of the dynamics of natural scenes. Naively, doing so is made
difficult by the O(N^6) computational complexity in the number of pixels N for
learning of the Lie group operators, and an abundance of local minima while
inferring transformations for specific image sequences. We present solutions to
both of these difficulties, reducing learning to O(N^2) complexity via a
re-parameterization of the Lie group operators, and introducing "blurring"
operators that allows inference to escape local minima via a transformation
specific reduction in scale. Both learning and inference is demonstrated using
these extensions for the full set of affine transformations. |
Year | Venue | Keywords |
---|---|---|
2010 | Clinical Orthopaedics and Related Research | affine transformation,local minima,linear transformation,parameter estimation,computational complexity,distance transform,lie group,pattern recognition |
DocType | Volume | Citations |
Journal | abs/1001.1 | 6 |
PageRank | References | Authors |
0.67 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jascha Sohl-Dickstein | 1 | 673 | 82.82 |
Jimmy C. Wang | 2 | 6 | 0.67 |
Bruno A. Olshausen | 3 | 493 | 66.79 |