A recurrent model of transformation invariance by association
A recurrent model of transformation invariance by association
复制标题
DOI：
10.1016/s0893-6080(99)00096-9
复制
发表时间：
2000-03-01
期刊：
影响因子：
7.8
通讯作者：
Renart, A
中科院分区：
文献类型：
--
作者：
Elliffe, MCM;Rolls, ET;Renart, A
本文描述了一种递归人工神经网络，它使用关联建立变换不变的表示的调查。模拟实现了Parga和Rolls [（1998）.递归网络中的关联变换不变识别。神经计算10（6），1507 - 1525。它定义了多个（例如，"视图"）模式将在共享的首先，示出了网络可以存储并正确地从定义该对象的任何一个视图中检索"对象"表示，具有如分析预测的容量。新的结果扩展了分析，表明正确的物体检索可能发生在检索线索被扭曲的地方;不同物体的视图之间存在某种联系;连通性被稀释，即使这种稀释是不对称的。模拟还扩展了分析，表明该系统可以很好地与稀疏模式;并显示模式稀疏性如何与每个对象的视图数量相互作用（作为模式编码的统计特性的结果），以提供可预测的对象检索性能。因此，有用的结果扩展了不变模式识别的经常性模型。(C)2000爱思唯尔科技有限公司版权所有。
This paper describes an investigation of a recurrent artificial neural network which uses association to build transform-invariant representations. The simulation implements the analytic model of Parga and Rolls [(1998). Transform-invariant recognition by association in a recurrent network. Neural Computation 10(6), 1507-1525.] which defines multiple (e.g. "view") patterns to be within the basin of attraction of a shared (e.g. "object") representation.First, it was shown that the network could store and correctly retrieve an "object" representation from any one of the views which define that object, with capacity as predicted analytically.Second, new results extended the analysis by showing that correct object retrieval could occur where retrieval cues were distorted; where there was some association between the views of different objects; and where connectivity was diluted, even when this dilution was asymmetric. The simulations also extended the analysis by showing that the system could work well with sparse patterns; and showing how pattern sparseness interacts with the number of views of each object (as a result of the statistical properties of the pattern coding) to give predictable object retrieval performance. The results thus usefully extend a recurrent model of invariant pattern recognition. (C) 2000 Elsevier Science Ltd. All rights reserved.