Fast Transformation-Invariant Component Analysis

  title={Fast Transformation-Invariant Component Analysis},
  author={Anitha Kannan and Nebojsa Jojic and Brendan J. Frey},
  journal={International Journal of Computer Vision},
Dimensionality reduction techniques such as principal component analysis and factor analysis are used to discover a linear mapping between high-dimensional data samples and points in a lower-dimensional subspace. Previously, Frey and Jojic introduced transformation-invariant component analysis (TCA) to learn a linear mapping, invariant to a set of known form of global transformations. However, parameter estimation in that model using the previously-proposed expectation maximization (EM… CONTINUE READING