Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Dilated CNN
Machine learning

Dilated CNN

Dilated Convolutional Network (WaveNet / Temporal Convolutional Network) · Also known as: Dilate Edilmiş CNN (WaveNet / TCN), WaveNet, Temporal Convolutional Network, TCN, dilated convolution

A Dilated CNN is a one-dimensional convolutional network whose receptive field grows exponentially with depth, letting it model long-range structure in time series and audio signals. WaveNet (van den Oord et al., 2016) and the Temporal Convolutional Network of Bai, Kolter and Koltun (2018) are the prominent members of this family.

ScholarGate
  1. Machine learning
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Dilated CNN
Bidirectional RNNGRURandom ForestSequence-to-Sequence Mod…XGBoostCNN Image ClassificationTextCNN

When to use it

Use a Dilated CNN for forecasting or prediction on continuous, sequential time-series data when long-range dependencies matter and you have at least a few hundred observations. It does not assume normally distributed data, but it needs sequential data, benefits strongly from a GPU, and the receptive-field size should be matched to the task. Below about 500 observations it tends to overfit, and below roughly 100 a deep convolutional model is not worth training.

Strengths & limitations

Strengths
  • Receptive field grows exponentially with depth, capturing long-range dependencies with few layers.
  • Convolutions parallelise well, training faster than recurrent networks on long sequences.
  • No normality assumption; works directly on continuous sequential signals.
  • Proven on demanding tasks, from WaveNet raw-audio generation to general TCN sequence modelling.
Limitations
  • Needs a fairly large training set — overfits when n is below about 500.
  • A GPU is effectively required for practical training.
  • The receptive-field size must be tuned to the task; too small a field misses long dependencies.
  • Deep convolutional sequence training is not meaningful on very short series (n below about 100).

Frequently asked

Why dilation instead of just a deeper network?

Dilation lets the receptive field grow exponentially rather than linearly with depth, so a few layers can reach thousands of past steps while keeping the parameter count and computation modest.

How does it compare to recurrent networks?

Bai, Kolter and Koltun (2018) found that convolutional architectures like the TCN often match or beat recurrent networks on sequence tasks, and they train faster because convolutions parallelise across time.

How much data do I need?

Plan for at least a few hundred sequential observations. Below about 500 the model tends to overfit, and below roughly 100 training a deep convolutional model is not worthwhile — a tree-based model is safer.

Do I need a GPU?

A GPU is strongly recommended; without one, training on long sequences becomes impractically slow.

Sources

  1. van den Oord, A. et al. (2016). WaveNet: A Generative Model for Raw Audio. arXiv. link ↗
  2. Bai, S., Kolter, J.Z. & Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv:1803.01271. link ↗

How to cite this page

ScholarGate. (2026, June 1). Dilated Convolutional Network (WaveNet / Temporal Convolutional Network). ScholarGate. https://scholargate.app/en/deep-learning/dilated-cnn

Related methods

Bidirectional RNNGRURandom ForestSequence-to-Sequence ModelXGBoost

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Bidirectional RNNDeep learning↔ compare
  • GRUDeep learning↔ compare
  • Random ForestMachine learning↔ compare
  • Sequence-to-Sequence ModelDeep learning↔ compare
  • XGBoostMachine learning↔ compare
Compare side by side →

Referenced by

CNN Image ClassificationTextCNN

Similar methods

SCINetConvolutional Neural NetworkLSTMMICNTimesNetNeural ODEN-BEATSN-HiTS

Related reference concepts

Convolutional and Sequence ModelsDeep LearningDeep Generative ModelsNeural Network ArchitecturesSequence-to-Sequence Models and TransformersBackpropagation and Optimization

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Dilated CNN (Dilated Convolutional Network (WaveNet / Temporal Convolutional Network)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/dilated-cnn · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
van den Oord, A. et al.; Bai, S., Kolter, J.Z. & Koltun, V.
Year
2016
Type
Deep learning (dilated 1D convolutional network)
Task
Time-series forecasting & sequence prediction
MinSample
200
Related methods
Bidirectional RNNGRURandom ForestSequence-to-Sequence ModelXGBoost
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account