The need for NNs

NNs have been around for many years, and they’ve gone through several periods, during which they’ve fallen in and out of favor. However, recently, they have steadily gained ground over many other competing machine learning algorithms. This resurgence is due to computers getting faster, the use of graphical processing units (GPUs) versus the most traditional use of central processing units (CPUs), better algorithms and NN design, and increasingly larger datasets, which we’ll look at in this book. To get an idea of their success, let’s look at the ImageNet Large Scale Visual Recognition Challenge (http://image-net.org/challenges/LSVRC/, or just ImageNet). The participants train their algorithms using the ImageNet database. It contains more than 1 million high-resolution color images in over 1,000 categories (one category may be images of cars, another of people, trees, and so on). One of the tasks in the challenge is to classify unknown images...