In this chapter, we will discuss about some basic concepts of deep learning and their related architectures that will be found in all the subsequent chapters of this book. We'll start with a brief definition of machine learning, whose techniques allow the analysis of large amounts of data to automatically extract information and to make predictions about subsequent new data. Then we'll move onto deep learning, which is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data.
Finally, we'll introduce deep learning architectures, the so-called Deep Neural Networks (DNNs)--these are distinguished from the more commonplace single hidden layer neural networks by their depth; that is, the number of node layers through which data passes in a multistep process of pattern recognition. we will provide a chart summarizing all the neural networks from where most of the deep learning algorithm evolved.
In the final part of the chapter, we'll briefly examine and compare some deep learning frameworks across various features, such as the native language of the framework, multi-GPU support, and aspects of usability.
This chapter covers the following topics:
- Introducing machine learning
- What is deep learning?
- Neural networks
- How does an artificial neural network learn?
- Neural network architectures
- DNNs architectures
- Deep learning framework comparison
