On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments
Peer reviewed, Journal article
Accepted version
Date
2021-08-19Metadata
Show full item recordCollections
Abstract
Associative memories enjoy many interesting properties in terms of error correction capabilities, robustness to noise, storage capacity and retrieval performance and their usage spans over a large set of applications. In this article, we investigate and extend Tournament-Based Neural Networks, originally proposed by Jiang et al. (2016), which is a novel sequence storage associative memory architecture with high memory efficiency and accurate sequence retrieval. We propose a more general method for learning the sequences which we call Feedback Tournament-Based Neural Networks. The retrieval process is also extended to both directions: forward and backward, i.e. any large-enough segment of a sequence can produce the whole sequence. Furthermore, two retrieval algorithms, Cache-Winner and Explore-Winner are introduced to increase the retrieval performance. Through simulation results, we shed light on the strengths and weaknesses of each algorithm.