.png){kind=icon}
返回
Modelling neural probabilistic computation using vector symbolic architectures
.png){kind=icon}
PRE
AI
DOI：10.1007/s11571-023-10031-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Distributed vector representations are a key bridging point between connectionist and symbolic representations in cognition. It is unclear how uncertainty should be modelled in systems using such representations. In this paper we discuss how bundles of symbols in certain Vector Symbolic Architectures (VSAs) can be understood as defining an object that has a relationship to a probability distribution, and how statements in VSAs can be understood as being analogous to probabilistic statements. The aim of this paper is to show how (spiking) neural implementations of VSAs can be used to implement probabilistic operations that are useful in building cognitive models. We show how similarity operators between continuous values represented as Spatial Semantic Pointers (SSPs), an example of a technique known as fractional binding, induces a quasi-kernel function that can be used in density estimation. Further, we sketch novel designs for networks that compute entropy and mutual information of VSA-represented distributions and demonstrate their performance when implemented as networks of spiking neurons. We also discuss the relationship between our technique and quantum probability, another technique proposed for modelling uncertainty in cognition. While we restrict ourselves to operators proposed for Holographic Reduced Representations, and for representing real-valued data. We suggest that the methods presented in this paper should translate to any VSA where the dot product between fractionally bound symbols induces a valid kernel.
Keyword:
Probability
Bayesian modelling
Vector symbolic architecture
Fractional binding
Spatial semantic pointers
期刊
IF:
3.9
论文数:
1.5K
被引数:
2.8K
机构
引用论文
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Association of some Campylobacter jejuni with Pseudomonas aeruginosa biofilms increases attachment under conditions mimicking those in the environment.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Competing reactions for poly(aryl ether ketone) synthesis: 2. Preparationof high molecular weight polymer from hydroquinoneand 1,3-bis(4-chlorobenzoyl)benzenePolymer
PolymerIF0
PREAI
分享收藏Vector Symbolic Architectures as a Computing Framework for Emerging HardwarePROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏
查看更多内容