Wuerfelspiel Based Training Data methods for ATR

摘要

A data object is constructed from a P x M Wuerfelspiel matrix W by choosing an entry from each column to construct a sequence A_0A_1 • A_(M-1) Each of the P~M possibilities are designed to correspond to the same category according to some chosen measure. This matrix could encode many types of data. 1. Musical fragments, all of which evoke sadness; each column entry is a 4 beat sequence with a chosen A_0A_1A_2 thus 16 beats long (W is P x 3). 2. Paintings, all of which evoke happiness; each column entry is a layer and a given A_0A_1A_2 is a painting constructed using these layers (W is P x 3). 3. feature vectors corresponding to action potentials evoked from a biological cell''s exposure to a toxin. The action potential is divided into four relevant regions and each column entry represents the feature vector of a region. A given A_0A_1A_2A_3 is then an ion of the excitable cell''s output (W is P x 4). 4. feature vectors corresponding to an object such as a face or vehicle. The object is divided into four categories each assigned an feature vector with the resulting concatenation an representation of the object (W is P x 4).. All of the examples above correspond to one particular measure (sad music, happy paintings, an introduced toxin, an object to recognize) and hence, when a Wiirfelspiel matrix is constructed, relevant training information for recognition is encoded that can be used in many algorithms. The focus of this paper is on the application of these ideas to automatic target recognition (ATR). In addition, we discuss a larger biologically based model of temporal cortex polymodal sensor fusion which can use the feature vectors extracted from the ATR Wuerfelspiel data.