[论文解读] Learning to See Analogies: A Connectionist Exploration

Douglas Blank|arXiv (Cornell University)|Jan 18, 2020

Cognitive Science and Education Research参考文献 119被引用 8

一句话总结

本文提出了 Analogator，一种递归连接主义网络，通过专门的关联训练程序，从示例中学习进行类比。通过学习将输入场景分割为前景和背景成分，该模型在接触多个类比后发展出类比推理能力，表明类比能力可从感知学习中涌现，而非预先编程。

ABSTRACT

This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed.

研究动机与目标

• 探究类比推理是否可从学习中涌现，而非预先定义于模型中。
• 开发一种统一低层次感知与高层次类比推理的计算框架。
• 训练一个递归网络，识别场景中的前景与背景成分，实现新情境间的类比迁移。
• 挑战大多数类比模型中类比机制预先定义的假设，表明此类机制可被学习。

提出的方法

• 使用专门的关联学习程序训练一种递归神经网络架构，将输入场景分割为前景与背景成分。
• 模型在类比问题对及其解法上进行训练，学习将输入映射到适当的类比结构。
• 训练过程通过最小化在源情境与目标情境之间预测正确类比映射的误差来实现。
• 网络通过识别多样化输入场景之间的结构相似性实现泛化，当它们共享潜在关系结构时，将其视为类比。
• 分析模型的内部表征，评估类比结构如何被编码与检索。
• 将该方法与其它类比生成的计算模型进行比较，强调其基于学习、以感知为基础的特性。

实验结果

研究问题

• RQ1 类比推理是否可从学习中涌现，而非显式地编程到模型中？
• RQ2 连接主义网络如何学习在多样化输入场景中识别并应用类比结构？
• RQ3 在训练示例的基础上，模型在多大程度上能泛化到新颖的、未见过的类比问题？
• RQ4 前景与背景的分割在神经网络中实现类比推理方面起到何种作用？
• RQ5 这种基于学习的方法与符号化或预定义机制的类比生成模型相比有何异同？

主要发现

• Analogator 在接受多样化的类比问题及其解答的训练后，成功学会在新情境之间进行类比。
• 模型将场景分割为前景与背景成分的能力，对识别类比结构并实现知识迁移至关重要。
• 泛化性能随训练数据量的增加而提升，表明类比推理源于对多个示例的接触。
• 该模型表明类比推理可建立在感知处理基础上，模糊了低层次感知与高层次认知之间的界限。
• 该方法提供了一个统一框架，将分类、识别与类比推理整合于单一连接主义架构之中。
• 局限性包括对输入表示的敏感性，以及在处理高度抽象或非感知类比时的挑战。