Understanding the approach
In order to better understand what we are going to build, we need to learn a little bit about neural networks – how they work and what are they built of. We will not dive deep into the details of how some big neural networks work internally as this is beyond the scope of this book. We will only cover topics that are essential for understanding the approach in our particular case.
Brief introduction to neural networks
For many people, AI seems to be an exciting new technology. However, the truth is that it was invented decades ago (the whole subject of deep learning dates back to the 1940s) and it simply became more popular in the 21st century. The reason is that today, unlike in the past, we have very powerful computers and zillions of gigabytes of data that can be fed into the neural nets in order to train them properly. This is why this concept has become so popular in the last decade or two.