An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

By Shaojie Bai, J. Kolter, Vladlen Koltun. 2018

6,867 citations recorded by the source corpus.

For most deep learning practitioners, sequence modeling is synonymous with recurrent networks. Yet recent results indicate that convolutional architectures can outperform recurrent networks on tasks such as audio synthesis and machine translation. Given a new sequence modeling task or dataset, which architecture should one use? We conduct a systematic evaluation of generic convolutional and recurrent architectures for sequence modeling. The models are evaluated across a broad range of standard tasks that are commonly used to benchmark recurrent networks. Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory. We conclude that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutional networks should be regarded as a natural starting point for sequence modeling tasks. To assist related work, we have made code available at this http URL .

Subfields: Artificial Intelligence, Model Architectures, Evaluation & Benchmarks, 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. Yoshua Bengio
  2. Mohit Bansal
  3. Quoc V. Le
  4. Sergey Levine
  5. Percy Liang
  6. Ruslan Salakhutdinov
  7. Jianfeng Gao
  8. Dacheng Tao

In Model Architectures

  1. Yoshua Bengio
  2. Ruslan Salakhutdinov
  3. Vladlen Koltun
  4. Christopher R'e
  5. Tri Dao
  6. J. Kolter
  7. Kyunghyun Cho
  8. Shaojie Bai

In Evaluation & Benchmarks

  1. Jitendra Malik
  2. Vladlen Koltun
  3. Philipp Krahenbuhl
  4. Stefan Roth
  5. Giovanni Maria Farinella
  6. Antonino Furnari
  7. Silvio Savarese
  8. Andrew Zisserman

In Signal Processing

  1. Yoshua Bengio
  2. Dong Yu
  3. Jinyu Li
  4. Deliang Wang
  5. Nima Mesgarani
  6. Wei-Ning Hsu
  7. Yossi Adi
  8. Lior Wolf

Citations in the corpus