Abstract. Many models of neural network-based associative memory have been proposed and studied. However, most of these models do not have a rejection mechanism and hence are not practical for many real-world associative memory problems. For example, in human face recognition, we are given a database of face images and the identity of each image. Given an input image, the task is to associate-when appropriate-the image with the corresponding name of the person in the database. However, the input image may be that of a stranger. In this case, the system should reject the input. In this paper, we propose a practical associative memory model that has a rejection mechanism. The structure of the model is based on the restricted Coulomb energy (RCE) network. The capacity of the proposed memory is described by two measures: the ability of the system to correctly identify known individuals, and the ability of the system to reject individuals who are not in the database. Experimental results are given which show how the performance of the system varies as the size of the database increases-up to 1000 individuals.
This paper presents simulations of the capacity and error correction capability of the two-level decoupled Hamming network. The simulation results presented here are compared to the theoretically predicted results derived in a related paper (Ikeda, Watta, and Hassoun, 1998). In this analysis, we study capacity as a function of system dimension, window size, and noise. It is demonstrated that the two-level memory has a large capacity in the case of uniform random fundamental patterns, and that there is close agreement between the theoretical and emperical results.
We investigate a template matching-based classifier system which uses local distance computations and a voting scheme. The proposed system has a mechanism to reject unknown patterns, and provides invariance to small amounts of translation. Experimental results are presented for 3 different types of face recognition problems: classification experiments where we measure the ability of the system to identify known individuals; falsepositive experiments where we measure the ability of the system to reject images of unknown individuals; and temporal experiments, where we measure the ahility of the system to recognize images of known individuals taken over a period of time (6 months). The results show that the proposed system performs well on all 3 of these problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.