On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments
Journal article, Peer reviewed
Published version
![Thumbnail](/bora-xmlui/bitstream/handle/11250/2992618/Mofrad.pdf.jpg?sequence=6&isAllowed=y)
View/ Open
Date
2021Metadata
Show full item recordCollections
- Department of Informatics [978]
- Registrations from Cristin [10237]
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 letter, we investigate and extend tournament-based neural networks, originally proposed by Jiang, Gripon, Berrou, and Rabbat (2016), 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—in other words, 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.