When using CNNs for non-image (times series) data prediction, what are some constraints or things to look out for as compared to image data?

To be more precise, I notice there are different types of layers in a CNN model, as described below, which seem to be particularly designed for image data.

A convolutional layer that extracts features from a source image. Convolution helps with blurring, sharpening, edge detection, noise reduction, or other operations that can help the machine to learn specific characteristics of an image.

A pooling layer that reduces the image dimensionality without losing important features or patterns.

A fully connected layer also known as the dense layer, in which the results of the convolutional layers are fed through one or more neural layers to generate a prediction.

Are these operations also applicable to non-image data (for example, times series)?


Usually, you need to ensure that your convolutions are causal, meaning that there is no information leakage from the future into the past. You could start by looking at this paper, which compares Temporal Convolutional Networks (TCN) with vanilla RNNs models.


You can use CNN for time-series data. The Convolutional Recurrent Neural Network (RCNN) is one of the examples.

Convolutional layers basically extract features from images. It is not related to time-series data processing.

Some CNNs (such as in ResNet, Highway Networks, and DenseNet) use some recurrent concepts to improve their prediction, but they all are within single datapoint reasoning. You can go through these concepts to improve your intuitions.

  • $\begingroup$ Maybe you should provide a link to a paper that describes the RCNN that you were thinking of. $\endgroup$
    – nbro
    Dec 6 '20 at 13:08

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.