In Chapter 9, we looked at how convolutional neural networks (CNNs) improve upon the traditional neural network architecture for image classification. Although CNNs perform very well for image classification in which image translation and rotation are taken care of, they do not necessarily help in identifying temporal patterns. Essentially, one can think of CNNs as identifying static patterns.
Recurrent neural networks (RNNs) are designed to solve the problem of identifying temporal patterns.