Karl E. Gustafson

Learn More
A second-order architecture is presented here for translation, rotation and scale invariant processing of 2-D images mapped to n input units. This new architecture has a complexity of O( n) weights as opposed to the O( n3 ) weights usually required for a third-order, rotation invariant architecture. The reduction in complexity is due to the use of discrete(More)
We showed previously that the first antieigenvalue and the components of the first antieigenvectors of an accretive compact normal operator can be expressed either by a pair of eigenvalues or by a single eigenvalue of the operator. In this paper, we pin down the eigenvalues of T that express the first antieigenvalue and the components of the first(More)
  • 1