A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data

TL;DR

This paper introduces a neural-symbolic-free, Bateson-inspired recursive method for generating hierarchical, human-readable semantic concepts from spatial sensory data, enabling reasoning and generalization without training.

Contribution

The paper presents a novel symbolic-only recursive approach based on Bateson's difference concept, avoiding heavy training and labeling in semantic concept generation from sensory data.

Findings

Produces rich, human-readable conceptual structures

Enables formal reasoning and high composability

Shows potential for generalization and out-of-distribution learning

Abstract

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.