Dreaming with ARC
Name
CBMM Memo 113.pdf
Size
1019.64 KB
Format
Adobe PDF
Checksum (MD5)
a5149d500573f9e0fb9971f6f6c87034
Author(s)
Banburski, Andrzej
Ghandi, Anshula
Alford, Simon
Dandekar, Sylee
Chin, Peter
Poggio, Tomaso
Date Issued
November 23, 2020
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo;113
Abstract
Current machine learning algorithms are highly specialized to whatever it is they are meant to do –– e.g. playing chess, picking up objects, or object recognition. How can we extend this to a system that could solve a wide range of problems? We argue that this can be achieved by a modular system –– one that can adapt to solving different problems by changing only the modules chosen and the order in which those modules are applied to the problem. The recently introduced ARC (Abstraction and Reasoning Corpus) dataset serves as an excellent test of abstract reasoning. Suited to the modular approach, the tasks depend on a set of human Core Knowledge inbuilt priors. In this paper we implement these priors as the modules of our system. We combine these modules using a neural-guided program synthesis.
Persistent DSpace Link
