Machine Learning For Dummies. John Paul Mueller
Читать онлайн книгу.
target="_blank" rel="nofollow" href="#fb3_img_img_60036427-ef5d-5a42-8c62-242f2aed6dd5.png" alt="Remember"/> This text usually contains an essential process or a bit of information that you must know to perform machine learning tasks successfully.
Beyond the Book
If you want to email us, please do! Make sure you send your book-specific requests to: [email protected]. We want to ensure that your book experience is the best one possible. The blog entries at http://blog.johnmuellerbooks.com/ contain a wealth of additional information about this book. You can check out John’s website at http://www.johnmuellerbooks.com/. You can also access other cool materials:
Cheat Sheet: A cheat sheet provides you with some special notes on things you can do with machine learning that not every other scientist knows. You can find the Cheat Sheet for this book at www.dummies.com. Type Machine Learning For Dummies in the Search box and click the Cheat Sheets option that appears.
Errata: You can find errata by entering this book’s title in the Search box at www.dummies.com, which takes you to this book’s page. In addition to errata, check out the blog posts with answers to reader questions and demonstrations of useful book-related techniques at http://blog.johnmuellerbooks.com/.
Companion files: The source code is available for download. All the book examples tell you precisely which example project to use. You can find these files at this book’s page at www.dummies.com. Just enter the book title in the Search box, click Books on the page that appears, click the book’s title, and scroll down the page to Downloads.We’ve also had trouble with the datasets used in the previous edition of this book. Sometimes the datasets change or might become unavailable. Given that you likely don’t want to download a large dataset unless you’re interested in that example, we’ve made the non-toy datasets (those available with a package) available at https://github.com/lmassaron/datasets. You don’t actually need to download them, though; the example code will perform that task for you automatically when you run it.
Where to Go from Here
Most people will want to start this book from the beginning, because it contains a good deal of information about how the real world view of machine learning differs from what movies might tell you. However, if you already have a first grounding in the reality of machine learning, you can always skip to the next part of the book.
Chapter 4 is where you want to go if you want to use a desktop setup, while Chapter 6 is helpful when you want to use a mobile device. Your preexisting setup may not work with the book’s examples because you might have different versions of the various products. It’s essential that you use the correct product versions to ensure success. Even if you choose to go with your own setup, consider reviewing Chapter 5 unless you’re an expert Python coder already.
If you’re already an expert with Python and know how machine learning works, you could always skip to Chapter 7. Starting at Chapter 7 will help you get into the examples quickly so that you spend less time with basics and more time with intermediate machine learning tasks. You can always go back and review the previous materials as needed.
Part 1
Introducing How Machines Learn
IN THIS PART …
Discovering how AI really works and what it can do for you
Considering what the term big data means
Understanding the role of statistics in machine learning
Defining where machine learning will take society in the future
Chapter 1
Getting the Real Story about AI
IN THIS CHAPTER
Artificial Intelligence (AI), the appearance of intelligence in machines, is a huge topic today, and it’s getting bigger all the time thanks to the success of new technologies (see some current examples at https://thinkml.ai/top-5-ai-achievements-of-2019/). However, most people are looking for everyday applications, such as talking to their smartphone. Talking to your smartphone is both fun and helpful to find out things like the location of the best sushi restaurant in town or to discover how to get to the concert hall. As you talk to your smartphone, it learns more about the way you talk and makes fewer mistakes in understanding your requests. The capability of your smartphone to learn and interpret your particular way of speaking is an example of an AI, and part of the technology used to make it happen is machine learning, the use of various techniques to allow algorithms to work better based on experience.
You likely make limited use of machine learning and AI all over the place today without really thinking about it. For example, the capability to speak to devices and have them actually do what you intend is an example of machine learning at work. Likewise, recommender systems, such as those found on Amazon, help you make purchases based on criteria such as previous product purchases or products that complement a current choice. The use of both AI and machine learning will only increase with time.
In this chapter, you delve into AI and discover what it means from several perspectives, including how it affects you as a consumer and as a scientist or engineer. You also discover that AI doesn’t equal machine learning, even though the media often confuse the two. Machine learning is definitely different from AI, even though the two are related.
Moving beyond the Hype
As any technology becomes bigger, so does the hype, and AI certainly has a lot of hype surrounding it. For one thing, some people have decided to engage in fear mongering rather than science. Killer robots, such as those found in the film The Terminator, really aren’t going to be the next big thing. Your first real experience with an android AI is more likely to be in the form a health care assistant (https://www.robotics.org/blog-article.cfm/The-Future-of-Elder-Care-is-Service-Robots/262)