Universal Recurrent Event Memories for Streaming Data

In this paper, we propose a new event memory architecture (MemNet) for recurrent neural networks, which is universal for different types of time series data such as scalar, multivariate or symbolic. Unlike other external neural memory architectures, it stores key-value pairs, which separate the info...

Full description

Saved in:
Bibliographic Details
Main Authors Dou, Ran, Principe, Jose
Format Journal Article
LanguageEnglish
Published 28.07.2023
Subjects
Online AccessGet full text

Cover

Loading…