The booming growth in the Machine Learning industry has brought renewed interest in people about Artificial Intelligence and what it’s really about. Although movies like The Terminator, along with all its sequels and prequels have given most people a pretty good idea regarding what Artificial Intelligence is capable of, everyone wants to know what stage AI research is in at the moment and how far it can go. Can the AI boom actually lead on to the global catastrophe that these Sci-Fi movies portray?
Knowing Machine Learning and Data Science can also land you a really high paying job. Whether you want to beat the competition in the job market or are just curious about the technology, here are five of our favorite books on Artificial Intelligence and Machine Learning related topics.
This book talks about the past, present, and future of Artificial Intelligence and Machine Learning, without going into too much detail. So even if you are from a non-Computer Science background, you will find this book easy to understand and interesting to read. In the book, Alpaydin stresses that long gone are the days when humans had to program algorithms to instruct a computer on what to do. With Machine Learning and a huge surge of available data, which Alpaydin aptly calls a ‘dataquake’, computers don’t need to be taught what to do anymore, as they can learn what to do by themselves. The book sites some examples of how Machine Learning is being used in our day to day lives, and how it is increasingly infiltrating our daily existence. Only the essentials of the different methods are discussed without any mathematical and programming detail, and this makes it a pleasant read for just about anyone.
This book is essentially targeted at Python programmers who already know a little bit of OpenCV. The book goes step by step by getting your feet wet with the basics of statistical learning, like regression and clustering before taking you through the more complex machine learning algorithms like Decision Trees and Bayesian Networks. Once you’re familiar with these concepts and have learned how to incorporate these using Open CV, the book will guide you into the most popular topic of the hour, which is Deep Learning. By the end of the book, you would have a good understanding of which algorithms should be applied to a machine learning application of your choice and you would be well on your way to applying them in solving any problem with machine learning.
- Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition by Sebastian Raschka
If you are interested in a more hands-on book that can help you learn Machine Learning and Deep Learning from the basic to advanced levels using Python, you will find this book very helpful. You will see how the Python open-source libraries like Sci-kit Learn and TensorFlow can help you in carrying out complex machine learning computations with ease. Sci-kit learn is basically for beginners to learn their way around machine learning while TensorFlow has more advanced capabilities, especially in the realm of image processing and recognition.
This is the second edition to the original book by the same title. If you have read the original copy, you will find that this one is a lot more up to date with the new TensorFlow deep learning library. Moreover, the Sci-Kit Learn portions have also been updated to include the new additions to the library. Through this book, you will learn to use the methodologies explained to build your own sentiment analysis application using data from social media websites.
This is basically intended as a textbook for undergrad and graduate students but can be an excellent read for anyone with a background in Computer Science, Math, and Statistics. It contains a good balance of both theory and practice, starting with the basics about Agents and Agent Architecture and building up to the design and implementation of your own AI agents. It focuses on learning by doing and includes interesting exercises at the end of each chapter to review the concepts learned. The book is also paired with online learning resources like animations, lecture slides, Python implementations of the algorithms mentioned in the book, demos, and other bonuses.
The book has been intelligently designed to cover ten different dimensions of AI through four basic agent tasks: a delivery robot, a diagnostic assistant, a tutoring system, and a trading agent. In short, it covers a wide range of topics in just the amount of detail you need to understand and apply the concepts without feeling overwhelmed.
Al Sweigart is known for his easy-going style of writing, paired with a great sense of humor, which make his books ideal for beginners and even kids, who are interested in learning to code.
There are some day-to-day tasks that we often find mundane and boring to do, like sending mails, working with spreadsheets and scraping data from the Internet. Through this book, you will learn how to use various Python modules and frameworks to not only free yourself from having to do these tasks manually, but to get more work done quickly. Although this is not strictly a book on machine learning per se, it is a great way to get yourself familiar with the bare bones of Python coding before moving on to the more complex concepts. A good follow up to this book would be the Python Data Science Handbook by Jake VanderPlas, which will help you get your hands dirty with some actual Machine Learning libraries like IPython, NumPy, Pandas, and others.