Associative Memories with Small World Connectivity
نویسندگان
چکیده
In this paper we report experiments designed to find the relationship between the different parameters of sparsely connected networks of perceptrons with small world connectivity patterns, acting as associative memories.
منابع مشابه
High Capacity, Small World Associative Memory Models NEIL DAVEY, LEE CALCRAFT and ROD ADAMS
Models of associative memory usually have full connectivity or if diluted, random symmetric connectivity. In contrast, biological neural systems have predominantly local, non-symmetric connectivity. Here we investigate sparse networks of threshold units, trained with the perceptron learning rule. The units are given position and are arranged in a ring. The connectivity graph varies between bein...
متن کاملLocally-Connected and Small-World Associative Memories in Large Networks
The performance of a locally-connected associative memories built from a onedimensional array of perceptrons with a fixed number of afferent connections per unit is investigated under conditions of increasing network size. The performance profile yields unexpected results, with a peak in performance when the network size is 2 to 3 times the number of connections per unit. This phenomenon is dis...
متن کاملConnectivity in Real and Simulated Associative Memories
Finding efficient patterns of connectivity in sparse associative memories is a difficult problem. It is, however, one that real neuronal networks, such as the mammalian cortex, must have solved. We have investigated computational models of sparsely connected associative memories and found that some patterns of connectivity produce both good performance and efficient use of resources. This could...
متن کاملGaussian and exponential architectures in small-world associative memories
The performance of sparsely-connected associative memory models built from a set of perceptrons is investigated using different patterns of connectivity. Architectures based on Gaussian and exponential distributions are compared to networks created by progressively rewiring a locally-connected network. It is found that while all three architectures are capable of good pattern-completion perform...
متن کاملConnectivity in Real and Evolved Associative Memories
Finding efficient patterns of connectivity in sparse associative memories is a difficult problem. It is, however, one that real neuronal networks, such as the mammalian cortex, must have solved. We have investigated evolved computational models of sparsely connected associative memories and found that some patterns of connectivity produce both good performance and efficient use of resources. Th...
متن کامل