熵异联想记忆
Entropic Hetero-Associative Memory
AI总结:
本文提出熵异联想记忆扩展,通过四维关系存储异模态对象对,并设计三种方法解决缺失线索问题,在MNIST和EMNIST上验证了高效检索性能。
摘要:
熵联想记忆通过有限表格作为媒介,将对象保存在二维关系或“记忆平面”中。记忆对象通过同时强化线索所使用的单元格来存储,实现了赫布学习规则的一种形式。存储对象在媒介上“重叠”,因此记忆是不确定的,并且在每个状态下具有熵值。检索操作从线索和这种不确定内容中构建对象。在本文中,我们提出了异联想情况下的扩展,其中这些性质得以保留。异联想对象对(可能来自不同领域和/或模态)保存在四维关系中。记忆检索操作选择一个高度不确定的二维记忆平面,该平面特定于输入线索;然而,没有线索可以从后者平面中检索对象。我们提出了三种增量方法来解决这种缺失线索问题,称为随机、采样与测试以及搜索与测试。该模型通过由分别选自MNIST和EMNIST语料库的手写数字和字母组成的复合回忆进行评估,使得线索数字检索其关联字母,反之亦然。我们展示了记忆性能,并使用所有三种方法说明了记忆检索操作。该系统在计算资源非常有限的情况下,显示出存储、识别和检索非常大对象集的潜力。
英文摘要:
The Entropic Associative Memory holds objects in a 2D relation or ``memory plane'' using a finite table as the medium. Memory objects are stored by reinforcing simultaneously the cells used by the cue, implementing a form of Hebb's learning rule. Stored objects are ``overlapped'' on the medium, hence the memory is indeterminate and has an entropy value at each state. The retrieval operation constructs an object from the cue and such indeterminate content. In this paper we present the extension to the hetero-associative case in which these properties are preserved. Pairs of hetero-associated objects, possibly of different domain and/or modalities, are held in a 4D relation. The memory retrieval operation selects a largely indeterminate 2D memory plane that is specific to the input cue; however, there is no cue left to retrieve an object from such latter plane. We propose three incremental methods to address such missing cue problem, which we call random, sample and test, and search and test. The model is assessed with composite recollections consisting of manuscripts digits and letters selected from the MNIST and the EMNIST corpora, respectively, such that cue digits retrieve their associated letters and vice versa. We show the memory performance and illustrate the memory retrieval operation using all three methods. The system shows promise for storing, recognizing and retrieving very large sets of object with very limited computing resources.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。