In this chapter, we begin a new discussion with machine learning through GPU-enabled Python. The end objective of these chapters is to encourage the user to develop applications to benefit the scientific AI community. The fundamental steps to write a machine learning-based program will be illustrated via use cases.
With the help of the use cases, we will establish how GPU-enabled Python and machine learning can work in tandem to facilitate processing and analysis of large datasets. We will look at the significance of big data management, deep learning, and other crucial concepts. Additionally, computational exercises will be revisited but with a machine learning approach. The solution assistance section will help you devise your own techniques to implement machine learning on the three unique problems discussed previously through chapters 6, 7, and 8. The chapter is divided into two parts—an initial introduction to machine learning, and a hands-on walkthrough for machine learning.
Keeping all the discussion pointers in mind, the chapter is divided into the following sections to make learning seamless:
- The significance of the dual advantage – an AI perspective
- The evolution of artificial intelligence
- The emergence of machine learning
- Introducing machine learning frameworks
- Introducing TensorFlow
- Introducing PyTorch
- Installing TensorFlow and PyTorch for GPUs
- Configuring TensorFlow on PyCharm and Google Colab
- Configuring PyTorch on PyCharm and Google Colab
- Machine learning with TensorFlow and PyTorch
- Writing your first GPU-accelerated machine learning programs
- Revisiting our computational exercises with a machine learning approach