DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning

06/15/2020
by   Kevin Ellis, et al.
0

Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages – systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A “wake-sleep” learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems. DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton's and Coulomb's laws. Concepts are built compositionally from those learned earlier, yielding multi-layered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly with experience.

READ FULL TEXT

page 1

page 12

page 14

page 15

research
05/25/2022

Inductive Learning of Complex Knowledge from Raw Data

One of the ultimate goals of Artificial Intelligence is to learn general...
research
03/31/2018

Synthesis of Differentiable Functional Programs for Lifelong Learning

We present a neurosymbolic approach to the lifelong learning of algorith...
research
07/06/2020

Learning to learn generative programs with Memoised Wake-Sleep

We study a class of neuro-symbolic generative models in which neural net...
research
06/17/2022

On the Bug-proneness of Structures Inspired by Functional Programming in JavaScript Projects

Language constructs inspired by functional programming have made their w...
research
02/11/2023

Languages with Decidable Learning: A Meta-theorem

We study expression learning problems with syntactic restrictions and in...
research
04/18/2023

A Neural Lambda Calculus: Neurosymbolic AI meets the foundations of computing and functional programming

Over the last decades, deep neural networks based-models became the domi...
research
10/31/2012

First Experiments with PowerPlay

Like a scientist or a playing child, PowerPlay not only learns new skill...

Please sign up or login with your details

Forgot password? Click here to reset