Sparse Associative Memory

Hoffmann Heiko

首页> 外文期刊>Neural computation >Sparse Associative Memory

【24h】

Sparse Associative Memory

机译：稀疏联想记忆

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

It is still unknown how associative biological memories operate. Hopfield networks are popular models of associative memory, but they suffer from spurious memories and low efficiency. Here, we present a new model of an associative memory that overcomes these deficiencies. We call this model sparse associative memory (SAM) because it is based on sparse projections from neural patterns to pattern-specific neurons. These sparse projections have been shown to be sufficient to uniquely encode a neural pattern. Based on this principle, we investigate theoretically and in simulation our SAM model, which turns out to have high memory efficiency and a vanishingly small probability of spurious memories. This model may serve as a basic building block of brain functions involving associative memory.

机译：关联的生物记忆如何运作仍是未知的。 Hopfield网络是关联存储器的流行模型，但是它们具有虚假存储器和低效率的缺点。在这里，我们提出了一种克服这些不足的联想记忆新模型。我们将此模型称为稀疏关联记忆（SAM），因为它基于从神经模式到模式特定神经元的稀疏投影。这些稀疏的投影已经显示出足以唯一编码神经模式。基于此原理，我们在理论上进行了研究，并在仿真中对我们的SAM模型进行了仿真，结果证明该模型具有较高的存储效率，并且虚假存储的可能性几乎为零。该模型可以用作涉及联想记忆的脑功能的基本构建块。

著录项

来源
《Neural computation》 |2019年第5期|998-1014|共17页
作者
Hoffmann Heiko;
展开▼
作者单位

HRL Labs, Malibu, CA 90265 USA;

展开▼
收录信息美国《科学引文索引》(SCI);美国《化学文摘》(CA);
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Memory capacity and information capacity of sparsely encoded associative memory with replacement units [J] . Ryota Miyata, Shinnosuke Muta, Koji Kurata Artificial life and robotics . 2010,第3期

机译：带替换单元的稀疏编码关联存储器的存储容量和信息容量
2. Coexistence of memory patterns and mixed states in a sparsely encoded associative memory model storing ultrametric patterns [J] . Kimoto T, Okada M Biological Cybernetics: Communication and Control in Organisms and Automata: = Nachrichtenubertragung, Nachrichtenverarbeitung, Steuerung und Regelung in Organismen und in Automaten . 2004,第4期

机译：存储超度量模式的稀疏编码关联存储模型中的存储模式和混合状态共存
3. Spatially Arranged Sparse Recurrent Neural Networks for Energy Efficient Associative Memory [J] . Neural Networks and Learning Systems, IEEE Transactions on . 2020,第1期

机译：空间排列的稀疏递归神经网络，用于高效节能的联想记忆
4. Transfer Learning with Sparse Associative Memories [C] . Quentin Jodelet, Vincent Gripon, Masafumi Hagiwara International Conference on Artificial Neural Networks . 2019

机译：稀疏联想记忆转移学习
5. Rewind-Remind: Investigating How Gamification of Memory Tasks Can Evaluate Associative Memory Performance in Healthy, Older Adults [D] . Abellanoza, Cheryl Kay. 2017

机译：提醒：研究记忆任务的游戏化如何评估健康的成年人的联想记忆性能
6. No Evidence for Improved Associative Memory Performance Following Process-Based Associative Memory Training in Older Adults [O] . Martin Bellander, Anne Eschen, Martin Lövdén, 2016

机译：基于证据的老年人基于过程的联想记忆训练后尚无改善联想记忆性能的证据
7. Kanerva's sparse distributed memory: An associative memory algorithm well-suited to the Connection Machine [O] . Rogers David 1988

机译：Kanerva的稀疏分布式内存：一种非常适合Connection Machine的关联内存算法
8. Kanerva's sparse distributed memory: An associative memory algorithm well-suited to the Connection Machine [R] . Rogers, David 1988

机译：Kanerva的稀疏分布式内存：一种非常适合连接机器的关联内存算法

Sparse Associative Memory

摘要

著录项

相似文献

相关主题

期刊订阅