In this chapter, we will look at the main components of a convolutional neural network (CNN): kernels and pooling layers. We will then look at how a typical network looks. We will then try to solve a classification problem with a simple convolutional network and try to visualize the convolutional operation. The purpose of this is to try to understand, at least intuitively, how the learning works.
© Umberto Michelucci 2019U. MichelucciAdvanced Applied Deep Learning https://doi.org/10.1007/978-1-4842-4976-5_3
3. Fundamentals of Convolutional Neural Networks
TOELT LLC, Dübendorf, Switzerland
One of the main components of CNNs are filters, which are square matrices that have dimensions nK × nK, where nK is an ...