Papers
arxiv:1503.01007

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

Published on Jun 1, 2015
Authors:
,

Abstract

Standard deep learning and recurrent networks struggle with algorithmically generated sequence prediction tasks that require counting and memorization, but augmenting a recurrent network with trainable memory enables learning basic algorithms from sequential data.

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 1503.01007
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1503.01007 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1503.01007 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1503.01007 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.