Oct 17, 2014 · We consider a simple class of programs that can be evaluated with a single left-to-right pass using constant memory. Our main result is that ...

Learning to Execute. This software allows to train a Recurrent Neural Network (RNN) with Long-Short Term Memory (LSTM) units on short snippets of python code.

This presents an interesting machine learning challenge: can we predict runtime errors in a "static" setting, where program execution is not possible?

Abstract. Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and ...

This work developed a new variant of curriculum learning that improved the networks' performance in all experimental conditions and had a dramatic impact on ...

Oct 23, 2020 · We propose evaluating systematic generalization on learning to execute using control flow graphs, which tests sequential reasoning and use of program structure.

We study these generalization issues at the level of numerical subroutines that comprise common algorithms like sorting, shortest paths, and minimum spanning ...

In this work, we study this problem by learning to imitate the composable subroutines that form the basis of common algorithms, namely selection sort, merge ...

can be evaluated with a single left-to-right pass. ○ operations: addition, subtraction, multiplication, variable assignment, if- statement, and for-loops.

Recurrent Neural Networks (RNNs) with Long-Short Term Memory units (LSTM) are widely used because they are expressive and are easy to train.