**arXiv ID:** 1410.4615 **Authors:** Wojciech Zaremba, Ilya Sutskever **Published:** 2014-10-17T01:35:12Z **Abstract:** Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the sequence-to-sequence regime by training them to evaluate short computer programs, a domain that has traditionally been seen as too compl...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Learning To Execute?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-learning-to-execute)
# Learning to Execute
**arXiv ID:** 1410.4615
**Authors:** Wojciech Zaremba, Ilya Sutskever
**Published:** 2014-10-17T01:35:12Z
**Abstract:**
Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the sequence-to-sequence regime by training them to evaluate short computer programs, a domain that has traditionally been seen as too complex for neural networks. 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 LSTMs can learn to map the character-level representations of such programs to their correct outputs. Notably, it was necessary to use curriculum learning, and while conventional curriculum learning proved ineffective, we developed a new variant of curriculum learning that improved our networks' performance in all experimental conditions. The improved curriculum had a dramatic impact on an addition problem, making it possible to train an LSTM to add two 9-digit numbers with 99% accuracy.
## Skill Description
This skill is generated from the arXiv paper: Learning to Execute (1410.4615).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1410.4615](http://arxiv.org/abs/1410.4615v3)
