Abstract: We believe that many hallmarks of human intelligence, such as generalizing from limited experience, abstract reasoning and planning, analogical reasoning, creative problem solving, and capacity for language require the ability to consolidate experience into concepts, which act as basic building blocks of understanding and reasoning. We present a framework that defines a concept by an energy function over events in the environment, as well as an attention mask over entities participating in the event. Given few demonstration events, our method uses inference-time optimization procedure to generate events involving similar concepts or identify entities involved in the concept. We evaluate our framework on learning visual, quantitative, compositional, and relational concepts from demonstration events in an unsupervised manner. Our approach is able to successfully generate and identify concepts in a few-shot setting as well as transfer learned concepts between domains.
Keywords: concept learning, representation learning, energy models, meta-learning
TL;DR: Energy models combined with runtime optimization can generate and identify a range of concepts.