12 Convolutional Neural Networks (CNN)
12.1 Introduction
Convolutional Neural Networks [89] (CNN), are a category of neural networks that are specially designed to process data represented with a grid structure, such as images and time series data. The word “convolutional” indicates that convolutional networks use the mathematical operation of convolution. The convolution operation is introduced in CNNs to replace the general matrix multiplication in one or more layers of the network.
On the other hand, convolutional networks are quite similar to feedforward multilayer neural networks. They consist of inter-connected neurons, each of which receives multiple inputs from the preceding layer and then produces an output through an activation function. ...
Get Deep Learning in Time Series Analysis now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
