Convolutional Neural Networks (CNN) – Plan of Attack

If you go past the “convoluted” vocabulary (pun obviously intended), you will find that the plan of attack is set up in a way that will really help you dissect and absorb the concept.

The end goal is for you to understand what these networks are and how they operate.

As we get into that, you will get to see the differences and the similarities between Convolutional Neural Networks and your own brain, most particularly in the context of image recognition.

Get a grip on the basics before getting started.

The first building block in our plan of attack is convolution operation. In this step, we will touch on feature detectors, which basically serve as the neural network’s filters. We will also discuss feature maps, learning the parameters of such maps, how patterns are detected, the layers of detection, and how the findings are mapped out.

The second part of this step will involve the Rectified Linear Unit or ReLU. We will cover ReLU layers and explore how linearity functions in the context of Convolutional Neural Networks.

Not necessary for understanding CNN’s, but there’s no harm in a quick lesson to improve your skills.

In this part, we’ll cover pooling and will get to understand exactly how it generally works. Our nexus here, however, will be a specific type of pooling; max pooling. We’ll cover various approaches, though, including mean (or sum) pooling. This part will end with a demonstration made using a visual interactive tool that will definitely sort the whole concept out for you.

This will be a brief breakdown of the flattening process and how we move from pooled to flattened layers when working with Convolutional Neural Networks.

In this part, everything that we covered throughout the section will be merged together. By learning this, you’ll get to envision a fuller picture of how Convolutional Neural Networks operate and how the “neurons” that are finally produced learn the classification of images.

In the end, we’ll wrap everything up and give a quick recap of the concept covered in the section. If you feel like it will do you any benefit (and it probably will), you should check out the extra tutorial in which Softmax and Cross-Entropy are covered. It’s not mandatory for the course, but you will likely come across these concepts when working with Convolutional Neural Networks and it will do you a lot of good to be familiar with them.

A little extra to enhance your understanding of Convolutional Neural Networks.