hierarchical filtering
Efficient Computation of Complex Distance Metrics Using Hierarchical Filtering
By their very nature, memory based algorithms such as KNN or Parzen windows require a computationally expensive search of a large database of prototypes. In this paper we optimize the search(cid:173) ing process for tangent distance (Simard, LeCun and Denker, 1993) to improve speed performance. The closest prototypes are found by recursively searching included subset.s of the database using dis(cid:173) tances of increasing complexit.y. This is done by using a hierarchy of tangent distances (increasing the Humber of tangent. At each stage, a confidence level of the classification is computed.
Technology: