Evaluating the Apperception Engine

TL;DR

The paper evaluates the Apperception Engine, an unsupervised system that constructs symbolic causal theories from sensory data, demonstrating its effectiveness across diverse domains and outperforming neural networks and logic programming systems.

Contribution

It provides a comprehensive evaluation of the Apperception Engine's ability to predict, retrodict, and impute sensory data across multiple domains, showcasing its general-purpose applicability.

Findings

Outperforms neural nets and logic programming systems in various tasks.

Achieves human-level performance in sequence induction intelligence tests.

Excels in solving binding and occlusion problems.

Abstract

The Apperception Engine is an unsupervised learning system. Given a sequence of sensory inputs, it constructs a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the theory - objects, properties, and laws - must be integrated into a coherent whole. Once a theory has been constructed, it can be applied to predict future sensor readings, retrodict earlier readings, or impute missing readings. In this paper, we evaluate the Apperception Engine in a diverse variety of domains, including cellular automata, rhythms and simple nursery tunes, multi-modal binding problems, occlusion tasks, and sequence induction intelligence tests. In each domain, we test our engine's ability to predict future sensor values, retrodict earlier sensor values, and impute missing sensory data. The engine performs well in all these domains, significantly outperforming neural net baselines and state of the art inductive logic programming systems. These results are significant because neural nets typically struggle to solve the binding problem (where information from different modalities must somehow be combined together into different aspects of one unified object) and fail to solve occlusion tasks (in which objects are sometimes visible and sometimes obscured from view). We note in particular that in the sequence induction intelligence tests, our system achieved human-level performance. This is notable because our system is not a bespoke system designed specifically to solve intelligence tests, but a general-purpose system that was designed to make sense of any sensory sequence.