Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation

TL;DR

This paper advocates for a hybrid neural-symbolic representation that unifies symbolic and nonsymbolic knowledge, workflows, and model lifecycle management to enhance AI integration.

Contribution

It introduces a novel hybrid representation framework that models AI entities, knowledge types, and workflows, enabling effective integration and traceability.

Findings

Supports representation of both symbolic and nonsymbolic knowledge

Enables tracking of model changes and workflows

Facilitates integration of AI models and processes

Abstract

In this paper, we present our position for a neuralsymbolic integration strategy, arguing in favor of a hybrid representation to promote an effective integration. Such description differs from others fundamentally, since its entities aim at representing AI models in general, allowing to describe both nonsymbolic and symbolic knowledge, the integration between them and their corresponding processors. Moreover, the entities also support representing workflows, leveraging traceability to keep track of every change applied to models and their related entities (e.g., data or concepts) throughout the lifecycle of the models.