A Minimal Architecture for General Cognition

TL;DR

The paper introduces MANIC, a minimalistic cognitive architecture with only three models and a state machine, capable of achieving functional equivalence with complex architectures through theoretical analysis.

Contribution

It presents a simple yet theoretically sufficient architecture for general cognition, emphasizing established data science constructs over biological inspiration.

Findings

The architecture is theoretically capable of universal cognitive functions.

It can be practically trained despite its minimal components.

Provides a formal analysis supporting its sufficiency.

Abstract

A minimalistic cognitive architecture called MANIC is presented. The MANIC architecture requires only three function approximating models, and one state machine. Even with so few major components, it is theoretically sufficient to achieve functional equivalence with all other cognitive architectures, and can be practically trained. Instead of seeking to transfer architectural inspiration from biology into artificial intelligence, MANIC seeks to minimize novelty and follow the most well-established constructs that have evolved within various sub-fields of data science. From this perspective, MANIC offers an alternate approach to a long-standing objective of artificial intelligence. This paper provides a theoretical analysis of the MANIC architecture.