.png){kind=icon}
返回
GrapHD: Graph-Based Hyperdimensional Memorization for Brain-Like Cognitive Learning
.png){kind=icon}
OA
AI
DOI：10.3389/fnins.2022.757125.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Memorization is an essential functionality that enables today's machine learning algorithms to provide a high quality of learning and reasoning for each prediction. Memorization gives algorithms prior knowledge to keep the context and define confidence for their decision. Unfortunately, the existing deep learning algorithms have a weak and nontransparent notion of memorization. Brain-inspired HyperDimensional Computing (HDC) is introduced as a model of human memory. Therefore, it mimics several important functionalities of the brain memory by operating with a vector that is computationally tractable and mathematically rigorous in describing human cognition. In this manuscript, we introduce a brain-inspired system that represents HDC memorization capability over a graph of relations. We propose GrapHD, hyperdimensional memorization that represents graph-based information in high-dimensional space. GrapHD defines an encoding method representing complex graph structure while supporting both weighted and unweighted graphs. Our encoder spreads the information of all nodes and edges across into a full holistic representation so that no component is more responsible for storing any piece of information than another. Then, GrapHD defines several important cognitive functionalities over the encoded memory graph. These operations include memory reconstruction, information retrieval, graph matching, and shortest path. Our extensive evaluation shows that GrapHD: (1) significantly enhances learning capability by giving the notion of short/long term memorization to learning algorithms, (2) enables cognitive computing and reasoning over memorization graph, and (3) enables holographic brain-like computation with substantial robustness to noise and failure.
Keyword:
brain-inspired computing
hyperdimensional computing (HDC)
neuromorphic computing
machine leaning
memorization
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:
3.2
论文数:
1.6W
被引数:
5.3W
机构
引用论文
(V)TEAM for SPICE Simulation of Memristive Devices With Improved Numerical Performance.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏How Characteristics of a Rainfall Event and the Meteorological Conditions Determine the Development of Stemflow: A Case Study of a Birch Tree降雨事件的特征和气象条件如何决定树干流的发展: 以白桦树为例
OAAI
OAAI分享收藏Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors超维计算: 高维随机向量分布式表示计算简介
PREAI
分享收藏Alzheimer's disease: connecting findings from graph theoretical studies of brain networks阿尔茨海默氏病: 连接大脑网络图形理论研究的发现
PREAI
分享收藏分享收藏
查看更多内容