arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.13058cs.AI
收藏

熵联想记忆

An Entropic Associative Memory

Universidad Nacional Autónoma de México(墨西哥国立自治大学);Universidad de Guadalajara(瓜达拉哈拉大学)

Luis A. Pineda, Gibrán Fuentes, Rafael Morales

摘要:

自然记忆具有联想性、陈述性和分布性。符号计算记忆在其声明性特征上类似于自然记忆,并且信息可以显式地存储和恢复;然而,它们缺乏自然记忆的关联性和分布式特性。在联结主义或人工神经网络范式中开发的子符号记忆是关联的和分布式的,但不能表达符号结构,信息不能被显式地存储和检索;因此,它们缺乏陈述性属性。为了解决这个难题,我们使用不确定计算模型的关联内存寄存器,持有分布式表示的个别对象。这种计算模式有一个内在的计算熵,它衡量了表示的不确定性。此参数决定存储器的工作特性。关联寄存器嵌入在一个架构中,该架构将特定于模态的缓冲区中表达的具体图像映射为抽象表示,反之亦然,并且存储器系统作为一个整体满足自然存储器的三个属性。该系统已被用来模拟一个视觉记忆持有的手写数字的表示,识别和召回实验表明,有一个范围的熵值,不太低,也不太高,在联想记忆寄存器有一个令人满意的性能。在存储器检索操作中恢复的线索和对象之间的相似性取决于保存对应对象的表示的存储器寄存器的熵。使用标准计算机在模拟中实现实验,但是可以构建并行架构,其中存储器操作将采取非常减少数量的计算步骤。

英文摘要:

Natural memories are associative, declarative and distributed. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they lack the associative and distributed properties of natural memories. Sub-symbolic memories developed within the connectionist or artificial neural networks paradigm are associative and distributed, but are unable to express symbolic structure and information cannot be stored and retrieved explicitly; hence, they lack the declarative property. To address this dilemma, we use Relational-Indeterminate Computing to model associative memory registers that hold distributed representations of individual objects. This mode of computing has an intrinsic computing entropy which measures the indeterminacy of representations. This parameter determines the operational characteristics of the memory. Associative registers are embedded in an architecture that maps concrete images expressed in modality-specific buffers into abstract representations, and vice versa, and the memory system as a whole fulfills the three properties of natural memories. The system has been used to model a visual memory holding the representations of hand-written digits, and recognition and recall experiments show that there is a range of entropy values, not too low and not too high, in which associative memory registers have a satisfactory performance. The similarity between the cue and the object recovered in memory retrieve operations depends on the entropy of the memory register holding the representation of the corresponding object. The experiments were implemented in a simulation using a standard computer, but a parallel architecture may be built where the memory operations would take a very reduced number of computing steps.

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。

↑