Book Image

The Artificial Intelligence Infrastructure Workshop

By : Chinmay Arankalle, Gareth Dwyer, Bas Geerdink, Kunal Gera, Kevin Liao, Anand N.S.
Book Image

The Artificial Intelligence Infrastructure Workshop

By: Chinmay Arankalle, Gareth Dwyer, Bas Geerdink, Kunal Gera, Kevin Liao, Anand N.S.

Overview of this book

Social networking sites see an average of 350 million uploads daily - a quantity impossible for humans to scan and analyze. Only AI can do this job at the required speed, and to leverage an AI application at its full potential, you need an efficient and scalable data storage pipeline. The Artificial Intelligence Infrastructure Workshop will teach you how to build and manage one. The Artificial Intelligence Infrastructure Workshop begins taking you through some real-world applications of AI. You’ll explore the layers of a data lake and get to grips with security, scalability, and maintainability. With the help of hands-on exercises, you’ll learn how to define the requirements for AI applications in your organization. This AI book will show you how to select a database for your system and run common queries on databases such as MySQL, MongoDB, and Cassandra. You’ll also design your own AI trading system to get a feel of the pipeline-based architecture. As you learn to implement a deep Q-learning algorithm to play the CartPole game, you’ll gain hands-on experience with PyTorch. Finally, you’ll explore ways to run machine learning models in production as part of an AI application. By the end of the book, you’ll have learned how to build and deploy your own AI software at scale, using various tools, API frameworks, and serialization methods.
Table of Contents (14 chapters)
Preface
4
4. The Ethics of AI Data Storage

pickle and Flask

A machine learning model can “live” in (be part of) many different environments. The choice of environment should depend on the type of application that is being developed, the performance requirements, and the expected frequency of updates. For example, a model that has to predict the weather once per day for a weather analyst has different requirements than a model that makes friend suggestions for millions of people on a social network.

For extreme cases, there are specialized techniques such as streaming models. We’ll have a look at them later in this chapter. For now, we’ll focus on a method that works for most use cases: running a model as part of an API. In doing so, our model can be part of a microservices architecture, which gives a lot of flexibility and scalability. To build such an API, pickle and joblib are two popular libraries that can be used when working with Python models. They offer the possibility to capture a dataset...