Using matrices to model symbolic relationship
We describe a way of learning matrix representations of objects and relationships. The goal of learning is to allow multiplication of matrices to represent symbolic relationships between objects and symbolic relationships between relationships, which is the main novelty of the method. We demonstrate that this leads to excellent generalization in two different domains: modular arithmetic and family relationships. We show that the same system can learn first-order propositions such as $(2, 5) \member +\!3$ or $(Christopher, Penelope)\member has\_wife$, and higher-order propositions such as $(3, +\!3) \member plus$ and $(+\!3, -\!3) \member inverse$ or $(has\_husband, has\_wife)\in higher\_oppsex$. We further demonstrate that the system understands how higher-order propositions are related to first-order ones by showing that it can correctly answer questions about first-order propositions involving the relations $+\!3$ or $has\_wife$ even though it has not been trained on any first-order examples involving these relations.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSimilar Papers 제목 키워드 기반
A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning
A hallmark of human intelligence is the ability to infer abstract rules from limited experience and apply these rules to unfamiliar situations. This capacity is widely studied in the visual domain using the Raven's Progr…
One-Shot LearningDiagonal RNNs in Symbolic Music Modeling
In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compar…
Music ModelingA Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
Neither deep neural networks nor symbolic AI alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct ob…
Logical ReasoningOrthogonal Matrices for MBAT Vector Symbolic Architectures, and a "Soft" VSA Representation for JSON
Vector Symbolic Architectures (VSAs) give a way to represent a complex object as a single fixed-length vector, so that similar objects have similar vector representations. These vector representations then become easy to…
BIG-bench Machine LearningCombinatory Adjoints and Differentiation
We develop a compositional approach for automatic and symbolic differentiation based on categorical constructions in functional analysis where derivatives are linear functions on abstract vectors rather than being limite…