Shelly Goggin, Kristina Johnson, Karl Gustafson
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( n 3 ) weights usually required for a third-order, rotation invariant architecture. The reduction in complexity is due to the use of discrete frequency infor(cid:173) mation. Simulations show favorable comparisons to other neural network architectures.