.png){kind=icon}
返回
Competitive learning to generate sparse representations for associative memory
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.09.005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One of the most well established brain principles, Hebbian learning, has led to the theoretical concept of neural assemblies. Based on it, many interesting brain theories have spawned. Palm's work implements this concept through multiple binary Willshaw associative memories, in a model that not only has a wide cognitive explanatory power but also makes neuroscientific predictions. Yet, Willshaw's associative memory can only achieve top capacity when the stored vectors are extremely sparse (number of active bits can grow logarithmically with the vector's length). This strict requirement makes it difficult to apply any model that uses this associative memory, like Palm's, to real data. Hence the fact that most works apply the memory to optimal randomly generated codes that do not represent any information. This issue creates the need for encoders that can take real data, and produce sparse representations - a problem which is also raised following Barlow's efficient coding principle. In this work, we propose a biologically-constrained network that encodes images into codes that are suitable for Willshaw's associative memory. The network is organized into groups of neurons that specialize on local receptive fields, and learn through a competitive scheme. After conducting autoand hetero-association experiments on two visual data sets, we can conclude that our network not only beats sparse coding baselines, but also that it comes close to the performance achieved using optimal random codes. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Keyword:
Sparse coding
Associative memory
Autoencoders
Brain-inspired models
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.0K
被引数:
3.0W
机构
引用论文
17O solid-state NMR spectroscopy of A2B2O7oxides: quantitative isotopic enrichment and spectral acquisition?.png)
RSC AdvancesOAAI
RSC AdvancesIF0
OAAI分享收藏Attention Inspired Network: Steep learning curve in an invariant pattern recognition modelNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Radiocarbon and 210Pb distribution in submersible-taken deep-sea cores from Project FAMOUS著名项目的潜水深海岩心中的放射性碳和210Pb分布
PREAI
分享收藏Comparison of protein expression between human livers and the hepatic cell lines HepG2, Hep3B, and Huh7 using SWATH and MRM-HR proteomics: Focusing on drug-metabolizing enzymes使用SWATH和mrm-hr蛋白质组学比较人肝脏与肝细胞系HepG2，Hep3B和Huh7之间的蛋白质表达: 关注药物代谢酶OAAI
OAAI分享收藏
查看更多内容