Papers › Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

3 Mar 2015NeurIPS 2015 12arXiv:1503.01007archive 2025-07-28

Armand Joulin, Tomas Mikolov

Despite the recent achievements in machine learning, we are still very far from achieving real artificial intelligence. In this paper, we discuss the limitations of standard deep learning approaches and show that some of these limitations can be overcome by learning how to grow the complexity of a model in a structured way. Specifically, we study the simplest sequence prediction problems that are beyond the scope of what is learnable with standard recurrent networks, algorithmically generated sequences which can only be learned by models which have the capacity to count and to memorize sequences. We show that some basic algorithms can be learned from sequential data using a recurrent network associated with a trainable memory.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebook/Stack-RNN officialmentioned in papermentioned on GitHubNOASSERTION report
bdusell/stack-attention mentioned on GitHubpytorch report
fakeNetflix/facebook-repo-Stack-RNN mentioned on GitHubNOASSERTION report
yandexdataschool/AgentNet mentioned on GitHubNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections