Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
If I remember correctly, Convolutional neural networks (CNN) have first been developed for image classification purposes (see work from LeCun et al.).
The convolution process that "slides" over the input image is helpful indeed to detect some features.
Question: do you have examples of successful application of CNN for non-image data?
They can be employed wherever you can find meaningful adjacent patterns in the input. As an example, you can take a look at here for its use in NLP:
You can also read the well-known paper Convolutional Neural Networks for Sentence Classification which is about sentence classification.
