Year: 2024
Type: article
Abstract: As an intelligent software paradigm, neuro-symbolic systems – integrating neural networks and symbolic rules – have garnered increasing attention, with explosive growth in related research.However, existing approaches still struggle with the effective and efficient construction of large-scale neuro-symbolic systems.One key factor contributing to the unsatisfactory performance of neuro-symbolic learning is the incompatible management of uncertainty during both neural network training and symbolic rule learning processes.This paper aims to provide a systematic, consistent, and rigorous perspective to facilitate the discussion and analysis of the technical challenges in “end-to-end” neuro-symbolic learning.Based on this perspective, the paper organizes and reviews the ideas, progress, and current issues in related work, while also looking ahead to future directions in the development of this field.
Source: Scientia Sinica Informationis
Authors: Zenan LI, Yuan YAO, Xiaoxing MA, Jian LV
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4405881686