DeepAI AI Chat
Log In Sign Up

Unsupervised Hierarchical Concept Learning

by   Sumegh Roychowdhury, et al.

Discovering concepts (or temporal abstractions) in an unsupervised manner from demonstration data in the absence of an environment is an important problem. Organizing these discovered concepts hierarchically at different levels of abstraction is useful in discovering patterns, building ontologies, and generating tutorials from demonstration data. However, recent work to discover such concepts without access to any environment does not discover relationships (or a hierarchy) between these discovered concepts. In this paper, we present a Transformer-based concept abstraction architecture UNHCLE (pronounced uncle) that extracts a hierarchy of concepts in an unsupervised way from demonstration data. We empirically demonstrate how UNHCLE discovers meaningful hierarchies using datasets from Chess and Cooking domains. Finally, we show how UNHCLE learns meaningful language labels for concepts by using demonstration data augmented with natural language for cooking and chess. All of our code is available at


page 3

page 7

page 8


HINT: Hierarchical Neuron Concept Explainer

To interpret deep networks, one main approach is to associate neurons wi...

Concept Learning with Energy-Based Models

Many hallmarks of human intelligence, such as generalizing from limited ...

Expedition: A System for the Unsupervised Learning of a Hierarchy of Concepts

We present a system for bottom-up cumulative learning of myriad concepts...

Learning Task Decomposition with Ordered Memory Policy Network

Many complex real-world tasks are composed of several levels of sub-task...

Is it a Fruit, an Apple or a Granny Smith? Predicting the Basic Level in a Concept Hierarchy

The "basic level", according to experiments in cognitive psychology, is ...

Concept Algebra for Text-Controlled Vision Models

This paper concerns the control of text-guided generative models, where ...

Building Hierarchies of Concepts via Crowdsourcing

Hierarchies of concepts are useful in many applications from navigation ...