Library learning for neurally-guided Bayesian program induction
Name
8006-learning-libraries-of-subroutines-for-neurallyguided-bayesian-program-induction.pdf
Description
Published version
Size
383.85 KB
Format
Adobe PDF
Checksum (MD5)
084350da961d7b1864dff367f4583d94
Author(s)
Ellis, Kevin M.
Morales, Lucas E.
Sable-Meyer, Mathias
Solar Lezama, Armando
Tenenbaum, Joshua B
Date Issued
2018
Journal
Advances in Neural Information Processing Systems 31 (NIPS 2018)
Publisher
Curran Associates
Citation
Ellis, Kevin et al. "Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction." Advances in Neural Information Processing Systems 31 (NIPS 2018) © 2018 Curran Associates Inc
Version
Final published version
Abstract
Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain. We contribute a program induction algorithm called EC 2 that learns a DSL while jointly training a neural network to efficiently search for programs in the learned DSL. We use our model to synthesize functions on lists, edit text, and solve symbolic regression problems, showing how the model learns a domain-specific library of program components for expressing solutions to problems in the domain.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/8006-learning-libraries-of-subroutines-for-neurallyguided-bayesian-program-induction
