Cluster-based associative memories built from unreliable storage

Abstract

We consider associative memories based on clustered graphs that were recently introduced. These memories are almost optimal in terms of the amount of storage they require (efficiency), and allow retrieving messages with low complexity. We study an unreliable implementation of the memory and compare its error rate and storage efficiency with that of a reliable implementation. We present analytical and simulation results that indicate that the proposed memory structure can tolerate a large number of faults at a reasonable cost, thereby making it a good candidate for achieving highly efficient circuit implementations of associative memories.

Information, noise, coding, modulation: What about the brain?

“…Note also that this model involves only excitatory connections. Among other recent studies worth of mentioning about this kind of approach, we can cite [36] for improved diversity and [37] for resilience properties.…”