Abstract
This chapter discusses the concept of distributed associative memory (DAM), regression analysis, and attentive recognition. The indexing problem, that is, memory access by contents rather than by address, plays a central role for pattern recognition. A suitable model to solve the indexing problem is provided by the DAM. This model builds up the memory by associating pairs of key stimulus and response vectors via a matrix projection operator. The DAM scheme uses the Moore–Penrose generalized inverse to derive the memory operator. The DAM has several useful properties such as when the key vector is incomplete, the recalled vector resembles the original associated response data vector in a minimum squared error (MSE) sense and when the key vector is noisy the recalled vector is again optimal in the MSE sense. The chapter discusses the mathematical theory that draws analogies between the DAM and statistical regression theory. A DAM can be viewed as a distributed implementation of the prediction model from regression analysis.
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.
