Introduction to Deep Neural Networks (DNNs)

This chapter provides a high-level introduction to this textbook on assisting several statistical methods with deep learning. Specifically, deep learning is a prominent machine learning method, which is a subfield within artificial intelligence. As compared to some traditional machine learning methods, deep learning enjoys some other advanced features, including being free of feature engineering and scalability. It has already achieved many remarkable breakthroughs in many areas, such as image recognition and language processing. In addition to those achievements, deep learning also has a great potential to raise the performance bar in some real-world problems under non-standard settings, for example, hypothesis testing in adaptive clinical trials. For those deep-learning-assisted statistical methods to be introduced in later chapters, we specifically emphasize the importance of human intelligence to safeguard those integrated methods.