DeepAI AI Chat
Log In Sign Up

A Model of Fast Concept Inference with Object-Factorized Cognitive Programs

by   Daniel P. Sawyer, et al.
California Institute of Technology

The ability of humans to quickly identify general concepts from a handful of images has proven difficult to emulate with robots. Recently, a computer architecture was developed that allows robots to mimic some aspects of this human ability by modeling concepts as cognitive programs using an instruction set of primitive cognitive functions. This allowed a robot to emulate human imagination by simulating candidate programs in a world model before generalizing to the physical world. However, this model used a naive search algorithm that required 30 minutes to discover a single concept, and became intractable for programs with more than 20 instructions. To circumvent this bottleneck, we present an algorithm that emulates the human cognitive heuristics of object factorization and sub-goaling, allowing human-level inference speed, improving accuracy, and making the output more explainable.


page 1

page 2


Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs

Humans can infer concepts from image pairs and apply those in the physic...

Xapagy: a cognitive architecture for narrative reasoning

We introduce the Xapagy cognitive architecture: a software system design...

Translating Natural Language Instructions to Computer Programs for Robot Manipulation

It is highly desirable for robots that work alongside humans to be able ...

Communicating Natural Programs to Humans and Machines

The Abstraction and Reasoning Corpus (ARC) is a set of tasks that tests ...

Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs

Aiming to understand how human (false-)belief–a core socio-cognitive abi...

Learning a Deep Generative Model like a Program: the Free Category Prior

Humans surpass the cognitive abilities of most other animals in our abil...

Learning compositional programs with arguments and sampling

One of the most challenging goals in designing intelligent systems is em...