A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning

Hybridconnectionist symbolic systems have been the subject of muchrecent research in AI. By focusing on the implementation of highlevel human cognitive processes e.g., rule-based inference on low-level, brain-like structures e.g., neural networks, hybrid systems inherit both the e ciency of connectionism and the comprehensibility of symbolism. This paper presents the Basic Reasoning Applicator Implemented as a Neural Network BRAINN.Inspired by the columnar organisation of the human neocortex, BRAINN's architecture consists of a large hexagonal network of Hop eld nets, which encodes and processes knowledge from both rules and relations. BRAINN supports both rule-based reasoning and similarity-based reasoning. Empirical results demonstrate promise.

• Type: Conference
• Year: 1998
• Where: HYBRID
• Authors: Rafal Bogacz, Christophe G. Giraud-Carrier
• Keywords: Basic Reasoning Applicator, Control Systems, Human Cognitive Processes, HYBRID 1998, Neural Network