Evaluating the Apperception Engine

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.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1910.02227

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Recurrent World Models Facilitate Policy Evolution
• Model-Based Reinforcement Learning for Atari
• Graph networks as learnable physics engines for inference and control
• Learning Symbolic Models of Stochastic Domains
• Measuring abstract reasoning in neural networks
• Recurrent Environment Simulators
• Learning and Querying Fast Generative Models for Reinforcement Learning
• Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
• Composable Planning with Attributes
• On the adoption of abductive reasoning for time series interpretation