Neural Functional Programming

John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow

Nov 04, 2016 (modified: Nov 04, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: We discuss a range of modeling choices that arise when constructing an end-to-end differentiable programming language suitable for learning programs from input-output examples. Taking cues from programming languages research, we study the effect of memory allocation schemes, immutable data, type systems, and built-in control-flow structures on the success rate of learning algorithms. We build a range of models leading up to a simple differentiable functional programming language. Our empirical evaluation shows that this language allows to learn far more programs than existing baselines.
  • TL;DR: A differentiable functional programming language for learning programs from input-output examples.
  • Conflicts: microsoft.com
  • Keywords: Supervised Learning
  • Authorids: feser@csail.mit.edu, mabrocks@microsoft.com, t-algaun@microsoft.com, dtarlow@microsoft.com

Loading