Products
  • Wolfram|One

    The definitive Wolfram Language and notebook experience

  • Mathematica

    The original technical computing environment

  • Wolfram Notebook Assistant + LLM Kit

    All-in-one AI assistance for your Wolfram experience

  • System Modeler
  • Wolfram Player
  • Finance Platform
  • Wolfram Engine
  • Enterprise Private Cloud
  • Application Server
  • Wolfram|Alpha Notebook Edition
  • Wolfram Cloud App
  • Wolfram Player App

More mobile apps

Core Technologies of Wolfram Products

  • Wolfram Language
  • Computable Data
  • Wolfram Notebooks
  • AI & Linguistic Understanding

Deployment Options

  • Wolfram Cloud
  • wolframscript
  • Wolfram Engine Community Edition
  • Wolfram LLM API
  • WSTPServer
  • Wolfram|Alpha APIs

From the Community

  • Function Repository
  • Community Paclet Repository
  • Example Repository
  • Neural Net Repository
  • Prompt Repository
  • Wolfram Demonstrations
  • Data Repository
  • Group & Organizational Licensing
  • All Products
Consulting & Solutions

We deliver solutions for the AI era—combining symbolic computation, data-driven insights and deep technical expertise

  • Data & Computational Intelligence
  • Model-Based Design
  • Algorithm Development
  • Wolfram|Alpha for Business
  • Blockchain Technology
  • Education Technology
  • Quantum Computation

WolframConsulting.com

Wolfram Solutions

  • Data Science
  • Artificial Intelligence
  • Biosciences
  • Healthcare Intelligence
  • Sustainable Energy
  • Control Systems
  • Enterprise Wolfram|Alpha
  • Blockchain Labs

More Wolfram Solutions

Wolfram Solutions For Education

  • Research Universities
  • Colleges & Teaching Universities
  • Junior & Community Colleges
  • High Schools
  • Educational Technology
  • Computer-Based Math

More Solutions for Education

  • Contact Us
Learning & Support

Get Started

  • Wolfram Language Introduction
  • Fast Intro for Programmers
  • Fast Intro for Math Students
  • Wolfram Language Documentation

More Learning

  • Highlighted Core Areas
  • Demonstrations
  • YouTube
  • Daily Study Groups
  • Wolfram Schools and Programs
  • Books

Grow Your Skills

  • Wolfram U

    Courses in computing, science, life and more

  • Community

    Learn, solve problems and share ideas.

  • Blog

    News, views and insights from Wolfram

  • Resources for

    Software Developers

Tech Support

  • Contact Us
  • Support FAQs
  • Support FAQs
  • Contact Us
Company
  • About Wolfram
  • Career Center
  • All Sites & Resources
  • Connect & Follow
  • Contact Us

Work with Us

  • Student Ambassador Initiative
  • Wolfram for Startups
  • Student Opportunities
  • Jobs Using Wolfram Language

Educational Programs for Adults

  • Summer School
  • Winter School

Educational Programs for Youth

  • Middle School Camp
  • High School Research Program
  • Computational Adventures

Read

  • Stephen Wolfram's Writings
  • Wolfram Blog
  • Wolfram Tech | Books
  • Wolfram Media
  • Complex Systems

Educational Resources

  • Wolfram MathWorld
  • Wolfram in STEM/STEAM
  • Wolfram Challenges
  • Wolfram Problem Generator

Wolfram Initiatives

  • Wolfram Science
  • Wolfram Foundation
  • History of Mathematics Project

Events

  • Stephen Wolfram Livestreams
  • Online & In-Person Events
  • Contact Us
  • Connect & Follow
Wolfram|Alpha
  • Your Account
  • User Portal
  • Wolfram Cloud
  • Products
    • Wolfram|One
    • Mathematica
    • Wolfram Notebook Assistant + LLM Kit
    • System Modeler
    • Wolfram Player
    • Finance Platform
    • Wolfram|Alpha Notebook Edition
    • Wolfram Engine
    • Enterprise Private Cloud
    • Application Server
    • Wolfram Cloud App
    • Wolfram Player App

    More mobile apps

    • Core Technologies
      • Wolfram Language
      • Computable Data
      • Wolfram Notebooks
      • AI & Linguistic Understanding
    • Deployment Options
      • Wolfram Cloud
      • wolframscript
      • Wolfram Engine Community Edition
      • Wolfram LLM API
      • WSTPServer
      • Wolfram|Alpha APIs
    • From the Community
      • Function Repository
      • Community Paclet Repository
      • Example Repository
      • Neural Net Repository
      • Prompt Repository
      • Wolfram Demonstrations
      • Data Repository
    • Group & Organizational Licensing
    • All Products
  • Consulting & Solutions

    We deliver solutions for the AI era—combining symbolic computation, data-driven insights and deep technical expertise

    WolframConsulting.com

    Wolfram Solutions

    • Data Science
    • Artificial Intelligence
    • Biosciences
    • Healthcare Intelligence
    • Sustainable Energy
    • Control Systems
    • Enterprise Wolfram|Alpha
    • Blockchain Labs

    More Wolfram Solutions

    Wolfram Solutions For Education

    • Research Universities
    • Colleges & Teaching Universities
    • Junior & Community Colleges
    • High Schools
    • Educational Technology
    • Computer-Based Math

    More Solutions for Education

    • Contact Us
  • Learning & Support

    Get Started

    • Wolfram Language Introduction
    • Fast Intro for Programmers
    • Fast Intro for Math Students
    • Wolfram Language Documentation

    Grow Your Skills

    • Wolfram U

      Courses in computing, science, life and more

    • Community

      Learn, solve problems and share ideas.

    • Blog

      News, views and insights from Wolfram

    • Resources for

      Software Developers
    • Tech Support
      • Contact Us
      • Support FAQs
    • More Learning
      • Highlighted Core Areas
      • Demonstrations
      • YouTube
      • Daily Study Groups
      • Wolfram Schools and Programs
      • Books
    • Support FAQs
    • Contact Us
  • Company
    • About Wolfram
    • Career Center
    • All Sites & Resources
    • Connect & Follow
    • Contact Us

    Work with Us

    • Student Ambassador Initiative
    • Wolfram for Startups
    • Student Opportunities
    • Jobs Using Wolfram Language

    Educational Programs for Adults

    • Summer School
    • Winter School

    Educational Programs for Youth

    • Middle School Camp
    • High School Research Program
    • Computational Adventures

    Read

    • Stephen Wolfram's Writings
    • Wolfram Blog
    • Wolfram Tech | Books
    • Wolfram Media
    • Complex Systems
    • Educational Resources
      • Wolfram MathWorld
      • Wolfram in STEM/STEAM
      • Wolfram Challenges
      • Wolfram Problem Generator
    • Wolfram Initiatives
      • Wolfram Science
      • Wolfram Foundation
      • History of Mathematics Project
    • Events
      • Stephen Wolfram Livestreams
      • Online & In-Person Events
    • Contact Us
    • Connect & Follow
  • Wolfram|Alpha
  • Wolfram Cloud
  • Your Account
  • User Portal
Wolfram Language & System Documentation Center
NetArrayLayer
  • See Also
    • NetArray
    • FunctionLayer
    • RandomArrayLayer
    • ThreadingLayer
    • NetChain
    • NetGraph
    • NetInitialize
    • NetTrain
    • NetExtract
  • Related Guides
    • Neural Network Layers
  • Tech Notes
    • Neural Networks in the Wolfram Language
    • See Also
      • NetArray
      • FunctionLayer
      • RandomArrayLayer
      • ThreadingLayer
      • NetChain
      • NetGraph
      • NetInitialize
      • NetTrain
      • NetExtract
    • Related Guides
      • Neural Network Layers
    • Tech Notes
      • Neural Networks in the Wolfram Language

NetArrayLayer[]

represents a layer that has no input and produces as output a constant array.

NetArrayLayer[opts]

includes options for the initial value of the array or output size.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Arguments  
Ports  
Parameters  
"Array"  
Possible Issues  
See Also
Tech Notes
Related Guides
History
Cite this Page
BUILT-IN SYMBOL
  • See Also
    • NetArray
    • FunctionLayer
    • RandomArrayLayer
    • ThreadingLayer
    • NetChain
    • NetGraph
    • NetInitialize
    • NetTrain
    • NetExtract
  • Related Guides
    • Neural Network Layers
  • Tech Notes
    • Neural Networks in the Wolfram Language
    • See Also
      • NetArray
      • FunctionLayer
      • RandomArrayLayer
      • ThreadingLayer
      • NetChain
      • NetGraph
      • NetInitialize
      • NetTrain
      • NetExtract
    • Related Guides
      • Neural Network Layers
    • Tech Notes
      • Neural Networks in the Wolfram Language

NetArrayLayer

NetArrayLayer[]

represents a layer that has no input and produces as output a constant array.

NetArrayLayer[opts]

includes options for the initial value of the array or output size.

Details and Options

  • NetArrayLayer is typically used in a NetGraph and allows a learned array to be used as an ordinary input to other layers. Without NetArrayLayer, all layer inputs must ultimately be derived from inputs to the entire net.
  • The array stored by NetArrayLayer will be learned during training.
  • The constant array stored in NetArrayLayer has the same dimensions as the output of NetArrayLayer.
  • NetArrayLayer["Array"->array] can be used to give an explicit value of the constant array.
  • When the constant array is not explicitly specified or is given as Automatic, it is added automatically when NetInitialize or NetTrain is used.
  • NetArrayLayer["Output"->{d1,d2,…}] can be used to fix the output size of the layer, which also fixes the size of the constant array.
  • The following training parameter can also be included:
  • LearningRateMultipliersAutomaticlearning rate multipliers for the array
  • NetArrayLayer[…][] returns the constant array.
  • The constant array can also be obtained from an initialized NetArrayLayer using NetExtract[layer,"Array"].
  • Options[NetArrayLayer] gives the list of default options to construct the layer. Options[NetArrayLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[NetArrayLayer[…]] gives a report about the layer.
  • Information[NetArrayLayer[…],prop] gives the value of the property prop of NetArrayLayer[…]. Possible properties are the same as for NetGraph.

Examples

open all close all

Basic Examples  (2)

Create a NetArrayLayer:

Create an initialized NetArrayLayer with output dimensions specified:

Extract the initialized array:

Scope  (7)

Arguments  (4)

Create a NetArrayLayer with unspecified output size:

Create a NetArrayLayer with output dimensions specified:

Define a higher-dimensional output:

Specify only some output sizes:

Ports  (1)

Provide the output sizes directly as an "Output" port specification:

Parameters  (2)

"Array"  (2)

Create a NetArrayLayer with a specific initial value for the array:

Use the array in an elementwise operation in a NetGraph:

Evaluate the graph:

Create a NetArrayLayer with fixed output array that is not changing during the training:

Possible Issues  (3)

NetArrayLayer does not accept symbolic arrays:

Dimensions of "Array" specification should be consistent with dims specification:

"Output" dimensions need to be fully specified in order to use NetInitialize:

See Also

NetArray  FunctionLayer  RandomArrayLayer  ThreadingLayer  NetChain  NetGraph  NetInitialize  NetTrain  NetExtract

Tech Notes

    ▪
  • Neural Networks in the Wolfram Language

Related Guides

    ▪
  • Neural Network Layers

History

Introduced in 2020 (12.2)

Wolfram Research (2020), NetArrayLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/NetArrayLayer.html.

Text

Wolfram Research (2020), NetArrayLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/NetArrayLayer.html.

CMS

Wolfram Language. 2020. "NetArrayLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/NetArrayLayer.html.

APA

Wolfram Language. (2020). NetArrayLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/NetArrayLayer.html

BibTeX

@misc{reference.wolfram_2025_netarraylayer, author="Wolfram Research", title="{NetArrayLayer}", year="2020", howpublished="\url{https://reference.wolfram.com/language/ref/NetArrayLayer.html}", note=[Accessed: 01-December-2025]}

BibLaTeX

@online{reference.wolfram_2025_netarraylayer, organization={Wolfram Research}, title={NetArrayLayer}, year={2020}, url={https://reference.wolfram.com/language/ref/NetArrayLayer.html}, note=[Accessed: 01-December-2025]}

Top
Introduction for Programmers
Introductory Book
Wolfram Function Repository | Wolfram Data Repository | Wolfram Data Drop | Wolfram Language Products
Top
  • Products
  • Wolfram|One
  • Mathematica
  • Notebook Assistant + LLM Kit
  • System Modeler

  • Wolfram|Alpha Notebook Edition
  • Wolfram|Alpha Pro
  • Mobile Apps

  • Wolfram Player
  • Wolfram Engine

  • Volume & Site Licensing
  • Server Deployment Options
  • Consulting
  • Wolfram Consulting
  • Repositories
  • Data Repository
  • Function Repository
  • Community Paclet Repository
  • Neural Net Repository
  • Prompt Repository

  • Wolfram Language Example Repository
  • Notebook Archive
  • Wolfram GitHub
  • Learning
  • Wolfram U
  • Wolfram Language Documentation
  • Webinars & Training
  • Educational Programs

  • Wolfram Language Introduction
  • Fast Introduction for Programmers
  • Fast Introduction for Math Students
  • Books

  • Wolfram Community
  • Wolfram Blog
  • Public Resources
  • Wolfram|Alpha
  • Wolfram Problem Generator
  • Wolfram Challenges

  • Computer-Based Math
  • Computational Thinking
  • Computational Adventures

  • Demonstrations Project
  • Wolfram Data Drop
  • MathWorld
  • Wolfram Science
  • Wolfram Media Publishing
  • Customer Resources
  • Store
  • Product Downloads
  • User Portal
  • Your Account
  • Organization Access

  • Support FAQ
  • Contact Support
  • Company
  • About Wolfram
  • Careers
  • Contact
  • Events
Wolfram Community Wolfram Blog
Legal & Privacy Policy
WolframAlpha.com | WolframCloud.com
© 2025 Wolfram
© 2025 Wolfram | Legal & Privacy Policy |
English