Unbounded Capacity Associative Memory for Real-valued Pattern Storage and Recall

Autor:	Fathi M. Salem
Rok vydání:	2021
Předmět:	Theoretical computer science Recall business.industry Computer science media_common.quotation_subject Deep learning Scalar (physics) Fidelity Function (mathematics) Content-addressable memory Key (cryptography) Artificial intelligence Differentiable function business media_common
Zdroj:	MWSCAS
DOI:	10.1109/mwscas47672.2021.9531698
Popis:	We describe an unbounded capacity Associative Memory which effectively stores and retrieves unrestricted real-valued data/patterns with fidelity. This Associative Memory arises from a gradient system of a (differentiable scalar) energy function, and thus can directly be incorporated within existing layers of computational Deep Learning (DL) frameworks. The design effort also describes two options for key pattern retrieval.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4ede0ddcbb548447cd51d6d618ac5213 https://doi.org/10.1109/mwscas47672.2021.9531698 Zobrazit plný text záznamu