Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Project
Neurocompositional AI
Embedding symbolic computation within neural computation via Tensor Product Representations This is the long term project to embed symbolic computation within neural computation via Tensor Product Representations, using continuous structured representations for deeper, more fluid…
Project
RM Roles
Can we encode tree structures into Tensor Product Representations (TPR’s) where the rank of the TPR doesn’t grow with the depth of the tree? Can we encode tree structures into Tensor Product Representations (TPR’s) where…
Project
TP Transformer
Increasing the compositional power of Transformer with Tensor Product Representations. This project seeks to improve the compositional power of the Transformer model by leveraging critical theoretical properties of Tensor Product Representations (TPR’s). Several new diagnostic…
Project
TP Blackboard
Implementing a Neural Blackboard with Tensor Product Representation encoded tree structures. The TP Blackboard model uses Tensor Product Representations (TPR’s) to represent a neural blackboard, which neural agents then use to communicate, coordinate, and compose…
Project
TPR Chunking
Neural Networks processing information as chunks of structured items, encoded into Tensor Product Representations. The theory of chunking developed out of George Miller’s study of working memory in humans (opens in new tab). It can…