DeepCoder: Learning to Write Programs

By Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow. 2016

625 citations recorded by the source corpus.

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network’s predictions to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver. Empirically, we show that our approach leads to an order of magnitude speedup over the strong non-augmented baselines and a Recurrent Neural Network approach, and that we are able to solve problems of difficulty comparable to the simplest problems on programming competition websites.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Code Generation & Program Synthesis, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Percy Liang
  3. Yoshua Bengio
  4. Quoc V. Le
  5. Sergey Levine
  6. Luke S. Zettlemoyer
  7. Jianfeng Gao
  8. Graham Neubig

In Information Systems

  1. Charles Sutton
  2. Miltiadis Allamanis
  3. Uri Alon
  4. Eran Yahav
  5. Rishabh Singh
  6. Omer Levy
  7. Michael Pradel
  8. Koushik Sen

In Natural Language Processing

  1. Graham Neubig
  2. Percy Liang
  3. Luke S. Zettlemoyer
  4. Mohit Bansal
  5. Quoc V. Le
  6. Jianfeng Gao
  7. Christopher D. Manning
  8. Jonathan Berant

In Code Generation & Program Synthesis

  1. Charles Sutton
  2. Rishabh Singh
  3. Miltiadis Allamanis
  4. Uri Alon
  5. Eran Yahav
  6. Michael Pradel
  7. Swarat Chaudhuri
  8. Marc Brockschmidt

In Signal Processing

  1. Yoshua Bengio
  2. Quoc V. Le
  3. Charles Sutton
  4. Oriol Vinyals
  5. Mohammad Norouzi
  6. Ruslan Salakhutdinov
  7. Lior Wolf
  8. Ilya Sutskever

Citations in the corpus