How to Represent Part-Whole Hierarchies in a Neural Network

Geoffrey E. Hinton

2022Neural Computation149 citationsDOI

Abstract

This article does not describe a working system. Instead, it presents a single idea about representation that allows advances made by several different groups to be combined into an imaginary system called GLOM.1 The advances include transformers, neural fields, contrastive representation learning, distillation, and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy that has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. If GLOM can be made to work, it should significantly improve the interpretability of the representations produced by transformer-like systems when applied to vision or language.

Topics & Concepts

InterpretabilityParsingTransformerComputer scienceArtificial intelligenceArtificial neural networkHierarchyRepresentation (politics)Parse treeNatural language processingTheoretical computer scienceMachine learningEngineeringVoltageEconomicsLawPolitical sciencePoliticsElectrical engineeringMarket economyNeural Networks and ApplicationsDomain Adaptation and Few-Shot LearningImage Retrieval and Classification Techniques