Abstract
ABSTRACT We consider high capacity mean square error (MSE) associative processors (APs) and the firstuse of multiple APs. The application considered is multi-class distortion-invariant pattern recognition (PR). 1 . INTRODUCTION APs are attractive solutions for difficult PR problems. Section 2 reviews the three APs weconsider. Section 3 describes our multi-class distorted object database and PR problem chosen. Section 4 describes the feature space input AP neuron representation space we use (feature spaceneurons are needed to reduce the number of neurons required, to provide some distortion invarianceand to reduce the training set size needed). Section 5 presents initial results (these show the needfor multiple APs). Section 6 advances our multiple AP concept and Section 7 notes our conclusions. 2. ASSOCIATIVE PROCESSORS Figure 1 shows the AP matrix-vector (M-V) processor considered and the dimensions of thematrix (), the input (x), and output () vectors where M x = and M is the number of stored vector
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
