Mdthbs

Router on a stick not connecting 2 different VLANs

What happened to the HDEV ISS Experiment? Is it over?

about to retire but not retired yet, employed but not working any more

How does Mercy remove conditions?

What is the name of this plot that has rows with two connected dots?

How to say "I only speak one which is English." in French?

Why does a sticker slowly peel off, but if it is pulled quickly it tears?

What is the loud noise of a helicopter when the rotors are not yet moving?

Does a Mace of Disruption's Frightened effect override undead immunity to the Frightened condition?

Set orthographic view using python?

Why does Windows store Wi-Fi passwords in a reversible format?

What are the occurences of total war in the Native Americans?

What's special ammo in Destiny 2?

Thought experiment and possible contradiction between electromagnetism and special relativity

Billiard balls collision

How many petaflops does it take to land on the moon? What does Artemis need with an Aitken?

What are the IPSE’s, the ASPE’s, the FRIPSE’s and the GRIPSE’s?

Talk interpreter

Where does learning new skills fit into Agile?

74S vs 74LS ICs

Why is strlen so complex in C?

How much does Commander Data weigh?

can you help me identify this aircraft?

To what extent should we fear giving offense?

Is Max Pooling and Conv used on anything else but images?

What is the practical differences between pooling types at convolution?What is a 1D Convolutional Layer in Deep Learning?Should the depth on convolutional layers be set to a figure divisible by 2?Match an image from a set of images : Combine traditional Computer vision + Deep Learning/CNNHow to use deep learning to add local (e.g. repairing) transformations to images?Why convolution over volume sums up across channels?What is the purpose of a 1x1 convolutional layer?Wrangling data for CNN

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ margin-bottom:0;
}

2

$begingroup$

Can you think of any domain of application, other than 2D images, where it could make sense to use max pooling or convolution?

Because the ONNX format allows for non 2D inputs. On the operators page (https://github.com/onnx/onnx/blob/master/docs/Operators.md#MaxPool) they say

dimensions for image case are (N x C x H x W), where N is the batch
size, C is the number of channels, and H and W are the height and the
width of the data. For non image case, the dimensions are in the form
of (N x C x D1 x D2 ... Dn)

And I did a search, and couldn't find an application where non images.

machine-learning convolution

share|improve this question

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  You can use a conv2D on text/tabular data as well!
  $endgroup$
  – Aditya
  11 hours ago
  

  
  
  
  

add a comment | 

2

$begingroup$

Can you think of any domain of application, other than 2D images, where it could make sense to use max pooling or convolution?

Because the ONNX format allows for non 2D inputs. On the operators page (https://github.com/onnx/onnx/blob/master/docs/Operators.md#MaxPool) they say

dimensions for image case are (N x C x H x W), where N is the batch
size, C is the number of channels, and H and W are the height and the
width of the data. For non image case, the dimensions are in the form
of (N x C x D1 x D2 ... Dn)

And I did a search, and couldn't find an application where non images.

machine-learning convolution

share|improve this question

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  You can use a conv2D on text/tabular data as well!
  $endgroup$
  – Aditya
  11 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

Can you think of any domain of application, other than 2D images, where it could make sense to use max pooling or convolution?

Because the ONNX format allows for non 2D inputs. On the operators page (https://github.com/onnx/onnx/blob/master/docs/Operators.md#MaxPool) they say

dimensions for image case are (N x C x H x W), where N is the batch
size, C is the number of channels, and H and W are the height and the
width of the data. For non image case, the dimensions are in the form
of (N x C x D1 x D2 ... Dn)

And I did a search, and couldn't find an application where non images.

machine-learning convolution

share|improve this question

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 11 hours ago

ZakCZakC

11122 bronze badges

New contributor

ZakC is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 11 hours ago

ZakCZakC

11122 bronze badges

2 Answers
2

active

oldest

votes

1

$begingroup$

As @Aditya mentioned, we can use 1D Convolutions and Max Pooling for text classification as well. It has been used in sentiment analysis and gives quite good performance too. See here and here.

Another useful application is in signal processing. Classifying data from sensors of all kinds is a task for CNNs.

You can develop a Human Activity Recognizer using 1D Convolutions. See
here.

But, why not use an RNN instead of a CNN?

RNNs require a higher level of data preprocessing and have low inference speed if you are running them on a smartphone ( or any other IoT device ). CNNs are pretty fast in this case.

Audio classification using MFCC is performed using 1D Convolutional NN. See here.

2D Convolutions are mainly used in image concerned ML tasks. They could extract spatial features from the 2D arrays ( an image ). In some cases, you can use them on 2D data which is not an image.

share|improve this answer

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

$endgroup$

add a comment | 

1

$begingroup$

Can you think of any domain of application, other than 2D images,
where it could make sense to use max pooling or convolution?

Convolutions and max pooling are both used in other areas. Here you can see both being used for text:
Text Classification using CNN

And they do not even have to be 2-dimensional. Here is another example with 1-dimensional audio data:
Keras Sequential Conv1D Model Classification

Convolutions and max pooling are used to build models with the assumption that features close to each other will have a stronger relation to each other. This is independent of the domain, so it does not matter if they are pixels in an image or words in a text.

share|improve this answer

edited 10 hours ago

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

$endgroup$

add a comment | 

Your Answer

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

ZakC is a new contributor. Be nice, and check out our Code of Conduct.

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f58211%2fis-max-pooling-and-conv-used-on-anything-else-but-images%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

1

$begingroup$

As @Aditya mentioned, we can use 1D Convolutions and Max Pooling for text classification as well. It has been used in sentiment analysis and gives quite good performance too. See here and here.

Another useful application is in signal processing. Classifying data from sensors of all kinds is a task for CNNs.

You can develop a Human Activity Recognizer using 1D Convolutions. See
here.

But, why not use an RNN instead of a CNN?

RNNs require a higher level of data preprocessing and have low inference speed if you are running them on a smartphone ( or any other IoT device ). CNNs are pretty fast in this case.

Audio classification using MFCC is performed using 1D Convolutional NN. See here.

2D Convolutions are mainly used in image concerned ML tasks. They could extract spatial features from the 2D arrays ( an image ). In some cases, you can use them on 2D data which is not an image.

share|improve this answer

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

$endgroup$

add a comment | 

1

$begingroup$

As @Aditya mentioned, we can use 1D Convolutions and Max Pooling for text classification as well. It has been used in sentiment analysis and gives quite good performance too. See here and here.

Another useful application is in signal processing. Classifying data from sensors of all kinds is a task for CNNs.

You can develop a Human Activity Recognizer using 1D Convolutions. See
here.

But, why not use an RNN instead of a CNN?

RNNs require a higher level of data preprocessing and have low inference speed if you are running them on a smartphone ( or any other IoT device ). CNNs are pretty fast in this case.

Audio classification using MFCC is performed using 1D Convolutional NN. See here.

2D Convolutions are mainly used in image concerned ML tasks. They could extract spatial features from the 2D arrays ( an image ). In some cases, you can use them on 2D data which is not an image.

share|improve this answer

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

$endgroup$

add a comment | 

$begingroup$

As @Aditya mentioned, we can use 1D Convolutions and Max Pooling for text classification as well. It has been used in sentiment analysis and gives quite good performance too. See here and here.

Another useful application is in signal processing. Classifying data from sensors of all kinds is a task for CNNs.

You can develop a Human Activity Recognizer using 1D Convolutions. See
here.

But, why not use an RNN instead of a CNN?

RNNs require a higher level of data preprocessing and have low inference speed if you are running them on a smartphone ( or any other IoT device ). CNNs are pretty fast in this case.

Audio classification using MFCC is performed using 1D Convolutional NN. See here.

2D Convolutions are mainly used in image concerned ML tasks. They could extract spatial features from the 2D arrays ( an image ). In some cases, you can use them on 2D data which is not an image.

share|improve this answer

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

$endgroup$

share|improve this answer

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

answered 10 hours ago

Shubham PanchalShubham Panchal

1,08511 silver badge1313 bronze badges

1

$begingroup$

Can you think of any domain of application, other than 2D images,
where it could make sense to use max pooling or convolution?

Convolutions and max pooling are both used in other areas. Here you can see both being used for text:
Text Classification using CNN

And they do not even have to be 2-dimensional. Here is another example with 1-dimensional audio data:
Keras Sequential Conv1D Model Classification

Convolutions and max pooling are used to build models with the assumption that features close to each other will have a stronger relation to each other. This is independent of the domain, so it does not matter if they are pixels in an image or words in a text.

share|improve this answer

edited 10 hours ago

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

$endgroup$

add a comment | 

1

$begingroup$

Can you think of any domain of application, other than 2D images,
where it could make sense to use max pooling or convolution?

Convolutions and max pooling are both used in other areas. Here you can see both being used for text:
Text Classification using CNN

And they do not even have to be 2-dimensional. Here is another example with 1-dimensional audio data:
Keras Sequential Conv1D Model Classification

Convolutions and max pooling are used to build models with the assumption that features close to each other will have a stronger relation to each other. This is independent of the domain, so it does not matter if they are pixels in an image or words in a text.

share|improve this answer

edited 10 hours ago

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

$endgroup$

add a comment | 

$begingroup$

Can you think of any domain of application, other than 2D images,
where it could make sense to use max pooling or convolution?

Convolutions and max pooling are both used in other areas. Here you can see both being used for text:
Text Classification using CNN

And they do not even have to be 2-dimensional. Here is another example with 1-dimensional audio data:
Keras Sequential Conv1D Model Classification

Convolutions and max pooling are used to build models with the assumption that features close to each other will have a stronger relation to each other. This is independent of the domain, so it does not matter if they are pixels in an image or words in a text.

share|improve this answer

edited 10 hours ago

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

$endgroup$

share|improve this answer

edited 10 hours ago

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges

answered 10 hours ago

Simon LarssonSimon Larsson

2,48511 gold badge44 silver badges1818 bronze badges