Perspectives of NeuroSymbolic IntegrationExtended Abstract

Recurrent Neural Networks - Models, Capacities, and Applications

计算机科学;物理学

Kai-Uwe Ku¨hnberger ; Helmar Gust ; Peter Geibel

PID  :  81901

学科分类：计算机科学（综合）

来源: CEUR

【 摘 要 】

There is an obvious tension between symbolic and subsymbolic theories, because both show complementary strengths and weak nesses in corresponding applications and underlying methodologies. The resulting gap in the foundations and the applicability of these approaches is theoretically unsatisfactory and practically undesirable. We sketch a theory that bridges this gap between symbolic and subsymbolic ap proaches by the introduction of a Toposbased semisymbolic level used for coding logical firstorder expressions in a homogeneous framework. This semisymbolic level can be used for neural learning of logical first order theories. Besides a presentation of the general idea of the frame work, we sketch some challenges and important open problems for future research with respect to the presented approach and the field of neuro symbolic integration, in general.