A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning
Scientific Abstract
Hybrid connectionist symbolic systems have been the subject of much recent research in AI. By focusing on the implementation of high- level human cognitive processes (e.g., rule-based inference) on low-level, brain-like structures (e.g., neural networks), hybrid systems inherit both the eciency 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.
Similar content
Temporally distinct reward and action prediction error signals during value learning and habit formation
Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
On the Infinite Width and Depth Limits of Predictive Coding Networks
A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning
Scientific Abstract
Hybrid connectionist symbolic systems have been the subject of much recent research in AI. By focusing on the implementation of high- level human cognitive processes (e.g., rule-based inference) on low-level, brain-like structures (e.g., neural networks), hybrid systems inherit both the eciency 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.