一种受贝特森启发的递归模型：用于从空间感官数据生成语义形式概念
A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data
AI总结：
针对神经符号方法中符号锚定需大量训练标注的问题，提出受贝特森差异理论启发的纯符号递归模型，无需训练即可从空间感官数据生成高可组合、支持推理与泛化的分层形式概念结构，为神经符号研究提供新视角。
摘要：
机器学习的神经符号方法融合了连接主义与符号主义方法的双重优势。通常而言，这类模型采用基于神经架构的首个模块从复杂数据中提取特征，随后这些特征会被符号引擎当作符号进行处理，符号引擎可提供推理、概念结构、可组合性、更优的泛化能力与分布外学习等多种可能性。然而，将符号锚定到感官数据的神经方法虽功能强大，但大部分情况下仍需大量训练与繁琐的标注工作。\n本文提出了一种全新的纯符号方法，可从复杂空间感官数据中生成分层概念结构。该方法以贝特森提出的“差异是思想或概念产生的关键”这一观点为基础。遵循他的设想，该模型通过在多变量数值流中计算基础的序列比较，从原始数据中提取原子特征。更高层级的构造则由这些特征通过递归过程中的进一步比较构建而成。在递归的任意阶段，都可借助形式概念分析（Formal Concept Analysis）从这些构造与特征中得到概念结构。\n实验结果表明，该模型无需训练即可生成相当丰富且人类可读的概念表示。此外，通过该模型得到的概念结构具备三大特性：（1）呈现出高可组合性，这有望支持“未见过”的概念生成；（2）支持形式化推理；（3）具备与生俱来的泛化与分布外学习能力。因此，该方法可为当前的神经符号研究提供一个有趣的研究视角。未来需开发一套训练方法，以便在更大规模的数据集上测试该模型。
英文摘要：
Neural-symbolic approaches to machine learning incorporate the advantages from both connectionist and symbolic methods. Typically, these models employ a first module based on a neural architecture to extract features from complex data. Then, these features are processed as symbols by a symbolic engine that provides reasoning, concept structures, composability, better generalization and out-of-distribution learning among other possibilities. However, neural approaches to the grounding of symbols in sensory data, albeit powerful, still require heavy training and tedious labeling for the most part. This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex spatial sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. Following his suggestion, the model extracts atomic features from raw data by computing elemental sequential comparisons in a stream of multivariate numerical values. Higher-level constructs are built from these features by subjecting them to further comparisons in a recursive process. At any stage in the recursion, a concept structure may be obtained from these constructs and features by means of Formal Concept Analysis. Results show that the model is able to produce fairly rich yet human-readable conceptual representations without training. Additionally, the concept structures obtained through the model (i) present high composability, which potentially enables the generation of 'unseen' concepts, (ii) allow formal reasoning, and (iii) have inherent abilities for generalization and out-of-distribution learning. Consequently, this method may offer an interesting angle to current neural-symbolic research. Future work is required to develop a training methodology so that the model can be tested against a larger dataset.
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。
