2013/01/26 by Amin Karbasi, Karbasi, Amin, Amir Hesam Salavati +5
Computer Science · Engineering · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Information Theory (cs.IT) #Neural Networks and Applications #Neural Networks and Reservoir Computing #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1301.6265
openalex publication_date 2013/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent advances in associative memory design through strutured pattern sets and graph-based inference algorithms have allowed the reliable learning and retrieval of an exponential number of patterns. Both these and classical associative memories, however, have assumed internally noiseless computational nodes. This paper considers the setting when internal computations are also noisy. Even if all components are noisy, the final error probability in recall can often be made exceedingly small, as we characterize. There is a threshold phenomenon. We also show how to optimize inference algorithm parameters when knowing statistical properties of internal noise.