What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Following the tasters with scikit-learn, Keras, and PyTorch in the previous chapter, in this chapter, we will move on to more end-to-end examples. These examples are more advanced in the sense that they include more complex transformations and model types.

We'll be predicting partner choices with sklearn, where we'll implement a lot of custom transformer steps and more complicated machine learning pipelines. We'll then predict house prices in PyTorch and visualize feature and neuron importance. After that, we will perform active learning to decide customer values together with online learning in sklearn. In the well-known case of repeat offender prediction, we'll build a model without racial bias. Last, but not least, we'll forecast time series of CO₂ levels.

Online learning in this context (as opposed to internet-based learning) refers to a model update strategy that incorporates training data that comes in sequentially. This can be useful in cases where the dataset is very big (often the case with images, videos, and texts) or where it's important to keep the model up to date given the changing nature of the data.

In many of these recipes, we've shortened the description to the most salient details in order to highlight particular concepts. For the full details, please refer to the notebooks on GitHub.

In this chapter, we'll be covering the following recipes:

Transforming data in scikit-learn
Predicting house prices in PyTorch
Live decisioning customer values
Battling algorithmic bias
Forecasting CO₂ time series

Key benefits

Get up and running with artificial intelligence in no time using hands-on problem-solving recipes

Explore popular Python libraries and tools to build AI solutions for images, text, sounds, and images

Implement NLP, reinforcement learning, deep learning, GANs, Monte-Carlo tree search, and much more

Description

Artificial intelligence (AI) plays an integral role in automating problem-solving. This involves predicting and classifying data and training agents to execute tasks successfully. This book will teach you how to solve complex problems with the help of independent and insightful recipes ranging from the essentials to advanced methods that have just come out of research. Artificial Intelligence with Python Cookbook starts by showing you how to set up your Python environment and taking you through the fundamentals of data exploration. Moving ahead, you’ll be able to implement heuristic search techniques and genetic algorithms. In addition to this, you'll apply probabilistic models, constraint optimization, and reinforcement learning. As you advance through the book, you'll build deep learning models for text, images, video, and audio, and then delve into algorithmic bias, style transfer, music generation, and AI use cases in the healthcare and insurance industries. Throughout the book, you’ll learn about a variety of tools for problem-solving and gain the knowledge needed to effectively approach complex problems. By the end of this book on AI, you will have the skills you need to write AI and machine learning algorithms, test them, and deploy them for production.

Who is this book for?

This AI machine learning book is for Python developers, data scientists, machine learning engineers, and deep learning practitioners who want to learn how to build artificial intelligence solutions with easy-to-follow recipes. You’ll also find this book useful if you’re looking for state-of-the-art solutions to perform different machine learning tasks in various use cases. Basic working knowledge of the Python programming language and machine learning concepts will help you to work with code effectively in this book.

What you will learn

Implement data preprocessing steps and optimize model hyperparameters

Delve into representational learning with adversarial autoencoders

Use active learning, recommenders, knowledge embedding, and SAT solvers

Get to grips with probabilistic modeling with TensorFlow probability

Run object detection, text-to-speech conversion, and text and music generation

Apply swarm algorithms, multi-agent systems, and graph networks

Go from proof of concept to production by deploying models as microservices

Understand how to use modern AI in practice

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

40 Algorithms Every Programmer Should Know

S$67.99

Artificial Intelligence with Python Cookbook

S$59.99

S$52.99

Total S$ 180.97

Filter reviews by

All

Amazon verified reviews

Isaac Dec 03, 2020

There are a number of survey books on the market for doing AI with python. I own many of them. Auffarth's approach here is unique in that it takes a do then explain the approach. The chapters are well structured with cookbook examples followed by in-depth explanations. What the author calls 'how to do it' then 'how it works.' The breath covered in the book is also impressive. everything from setting up a basic environment to deploying models into production. Applications range from typical deep learning stuff (like predicting housing prices) to image processing, audio applications, and fraud detection. This has become my latest 'go-to' book when I want to explore a new AI topic. I would recommend it to any data scientist looking to take their skills to the next level.

Amazon Verified review

Eric D. Weber Apr 26, 2021

This book has the right mixture of breadth and depth, which is extremely challenging in the (growing) group of AI literature. What I enjoy the most is that you can both learn a lot of Python and/or learn a lot about ML and Experimentation, depending on your focus. Maybe most important, it allows those newer or intermediate in the field to scale up quickly. For beginners and practitioners, there is a lot of value to be found in the 400+ pages.

Lucinda Linde Feb 19, 2021

"Example isn’t another way to teach, it is the only way to teach." ---Albert EinsteinDisclaimer: This review has been requested by the publisher, and I am giving my honest review of this book. This review is based on reading the book. As with any Cookbook, the proof is in the pudding. I intend to use some of these recipes on my own data sets to see if the techniques help me get better results.OverviewArtificial Intelligence with Python Cookbook by Ben Auffarth, is a jam-packed masterclass in applying AI to a selection of important business problems. The book will be helpful to someone who had made many models, and wants to up their game to using more sophisticated AI.What I love about this book:The examples are very relevant. There are over 20 examples which range from detecting anomalies as in Fraud Detection to Time Series to Customer Lifetime Value to modelling spread of disease and many more. These are all applications that have proven business or social ROI.Chapter 1 is filled with helpful tips to set up Google Colab and Jupyter Notebook, as well as ways to write better code. These include speeding up and parallelizing code, putting in progress bars, auto-reloading packages and more. There are also really useful visualization techniques such as correlation heat maps and pair plot. These are fast ways to get a bird's-eye view of exploratory data analysis (EDA).Each chapter is its own guidebook to using a particular technique. For example, I recently did a project on Time Series and got ok results. Chapter 2 gives me additional ways to utilize SARIMAX, which I will try out. There are also scripts using FBProphet, which may be a better way to address Time Series. The code examples are in the book, but also on GitHub for easy copy-and-pasting. The book explains the rationale behind the code.The examples used from chapter to chapter build on each other. The examples start with the basic, such as the iris classification problem, and model using a variety of neural networks. There are chapters on NLP, machine vision, audio files and even deploying AI in production.The visualizations are very helpful to understanding the insights that are being generated from the code. Having the code to make those visualizations is extremely helpful.I will use this book as a reference and starting point for trying out techniques I haven't before. Can't wait to try out the examples in the book.What I don't like about the bookFor topics that I am really unprepared to absorb, the book gives links to material that can cover the basics. It makes me wonder if this book could perhaps be the springboard to multiple books each of which takes a few techniques, and brings the reader up to speed more gently, with examples of increasing complexity so the core concepts can be learned.Overall, "Artificial Intelligence with Python Cookbook" is very well thought out and a fantastic one place to start upping one's game in applying AI to a variety of valuable applications.

Andreas Mueller Dec 09, 2020

I've been impressed by the wide overview of the book, which really spans the gamut of what AI means, from classification to search algorithms and A/B testing. The book focuses on some standard tools but also branches out to surface some lesser known libraries that can come in handy.While 468 pages can only give a taste of each topic, the book is jam-packed with examples and serves as a good starting point with plenty of references.

Murphy Choy Aug 26, 2021

The book is a great recipe book for folks who want quick results without going through reams of content. I love the easy to read structure of this book.

Artificial Intelligence with Python Cookbook: Proven recipes for applying AI algorithms and deep learning techniques using TensorFlow 2.x and PyTorch 1.6

What do you get with eBook?