Stack Exchange Network
Stack Exchange network consists of 181 Q&A communities including
Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.
Visit Stack Exchange
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
Anybody can ask a question
The best answers are voted up and rise to the top
8 years, 7 months ago
Can CNNs be used with input data which is not an image? The reason I'm asking is because the original image is often clipped in size because of border effects when doing the convolution.
But if the input is not an image, and I really need to use all the input data, is it possible to overcome the problem?
Oct 23, 2014 at 3:05
216 4 4 silver badges 12 12 bronze badges
Convolutional networks work so well because they exploit an assumption about with weight sharing. This is why they only work with data where that assumption hold.
The assumption is a spatial one. It is best explained with a picture, where you do not care where exactly something is, which is sometimes called translational invariance.
As long as that assumption holds on your data, you can apply it. Other modalities are e.g. audio or (to some extent) text.
Oct 23, 2014 at 9:13
13.4k 3 3 gold badges 37 37 silver badges 59 59 bronze badges
Nothing in the CNN method requires clipping of the input data - that is simply a design choice by the modeller.
I am not completely sure what you are asking for, but it seems that you are interested in the problem associated with the edges of the input matrix. Each pixel at the edge of the image is only captured in a single neuron in the first convolutional layer, making the information less used for classification (which reduces accuracy). Zero-padding is often used to overcome this problem, and could easily be used for other data types as well.
Jul 10, 2015 at 14:54
4,956 10 10 gold badges 41 41 silver badges 76 76 bronze badges
By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our
Accept all cookies
Necessary cookies only