In recent years, we have seen a huge interest in neural networks, which are successfully used in various areas—business, medicine, technology, geology, physics, and so on. Neural networks have come into practice wherever it is necessary to solve problems of forecasting, classification, or control. This approach is attractive from an intuitive point of view because it is based on a simplified biological model of the human nervous system. It arose from research in the field of artificial intelligence, namely, from attempts to reproduce the ability of biological nervous systems to learn and correct mistakes by modeling the low-level structure of the brain. Neural networks are compelling modeling methods that allow us to reproduce extremely complex dependencies because they are non-linear. Neural networks also cope better with the curse of dimensionality than other methods that don't allow modeling dependencies for a large number of variables.
In this chapter, we'll look at the basic concepts of artificial neural networks and show you how to implement neural networks with different C++ libraries. We'll also go through the implementation of the multilayer perceptron and simple convolutional networks and find out what deep learning is and what its applications are.
The following topics will be covered in this chapter:
- An overview of neural networks
- Delving into convolutional networks
- What is deep learning?
- Examples of using C++ libraries to create neural networks
- Understanding image classification using the LeNet architecture