Artificial Intelligence By Example: Acquire advanced AI, machine learning, and deep learning design skills, 2nd Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
From the Publisher
How would you describe AI, true AI (also known as AGI), and Strong AI in today’s scenario?
Artificial Intelligence is constantly evolving and has the potential to replicate humans in every field. It gets your system to think smart and learn intelligently.
Artificial General Intelligence (AGI) is not a proven scientific reality to this day. Machine learning and deep learning models are still trained on specific datasets to obtain pre-defined results. In contrast to strong AI, narrow AI is not intended to execute human cognitive skills, rather, it is limited to the use of software to learn or accomplish certain problem solving or reasoning errands. However, transfer learning and domain learning extend the scope of well-trained models to a certain extent.
Presently, AI is predominantly a branch of applied mathematics. Some models can produce art forms (image, music, etc.) but remain based on mathematical models that preclude the expression of emotions.
What's new in this second edition of Artificial Intelligence by Example?
Artificial Intelligence By Example, Second Edition serves as a starting point for you to understand how AI is built, with the help of intriguing and exciting examples. It will take you to the cutting edge of AI and beyond with innovations that improve existing solutions.
I have added many new AI, ML and DL models: ensemble algorithms, neuromorphic computing, genetic algorithms, hybrid neural networks driven by genetic algorithms, random forests, and more.
This edition also has new examples for hybrid neural networks, combining reinforcement learning (RL) and deep learning (DL), chained algorithms, combining unsupervised learning with decision trees, random forests, combining DL and genetic algorithms, conversational user interfaces (CUI) for chatbots, neuromorphic computing, and quantum computing.
What are the key takeaways you want readers to get from this book?
The critical takeaway can be summed up in one sentence: learn what AI is, how to build reliable programs, when to use AI, and where to apply it.
If we talk about the key aspects of AI that my book covers, it encapsulates the theories of machine learning, deep learning, and major AI algorithms. The reader will be able to grasp in detail the different stages of e-commerce including manufacturing, services, warehouses, and delivery. It further equips readers with AI solutions combined with IoT, open-source Python programs, cloud platforms, enhancing chatbots, and quantum computing.
By the time you've finished this book, you'll be able to speak as a no-nonsense AI specialist in any situation with knowledge and productive creativity.
"This book presents recent and upcoming innovations in artificial intelligence in an approachable and friendly way. The breadth of topics covered in the book is staggering, ranging from traditional methods like reinforcement learning and K-means clustering all the way to neuromorphic and quantum computing. If you want to be exposed to what AI researchers are working on today from a practitioner's perspective, I cannot recommend this book enough."--
Trevor Bekolay, Co-founder of Applied Brain Research, Co-author of Neural Modeling of Speech Processing and Speech Learning: An Introduction
"If you want a practical understanding of Artificial Intelligence, I recommend reading Denis Rothman's recent book Artificial Intelligence By Example, Second Edition. He's an excellent writer with practical, real-world experience, capable of teaching a wide range of AI algorithms."--
Adrian Rosebrock, Chief PyImageSearcher, PyImageSearch
"There aren't many books - especially in tech - that cross the 500-page mark and keep you as captivated as this one. The second edition of Denis Rothman's Artificial Intelligence By Example is a nice and easily digestible amalgam of the fundamentals of deep learning and intuitive examples that help you learn and use them in the real world. Rothman ends with a series of informative chapters about neuromorphic and quantum computing - a new field that is bound to keep researchers, chip manufacturers, and the overall technology enthusiast glued to what's next in the coming decade."--
Tarry Singh, Founder & CEO of deepkapha.ai, curae.ai, and Real AI Inc.
About the Author
Denis Rothman graduated from Sorbonne University and Paris-Diderot University, writing one of the very first word2matrix embedding solutions. Denis Rothman is the author of three cutting-edge AI solutions: one of the first AI cognitive chatbots more than 30 years ago; a profit-orientated AI resource optimizing system; and an AI APS (Advanced Planning and Scheduling) solution based on cognitive patterns that is now used worldwide in aerospace, rail, energy, apparel and many other fields. Designed initially as a cognitive bot for IBM, it then went on to become a robust APS solution used to this day.
- Publisher : Packt Publishing (February 28, 2020)
- Language : English
- Paperback : 578 pages
- ISBN-10 : 1839211539
- ISBN-13 : 978-1839211539
- Item Weight : 2.07 pounds
- Dimensions : 7.5 x 1.31 x 9.25 inches
- Best Sellers Rank: #651,664 in Books (See Top 100 in Books)
- Customer Reviews:
About the author
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
I did find it a bit rambling at times (with too much fluffy writing), quirky (he uses 'import numpy as ql' instead of 'import numpy as np'), and difficult to understand some of the real-world examples. The organization of the book also seems a little strange to me (quirky) although given the range of topics in the book, I'm not sure how to better organize it. Since it spans so many topics, it doesn't cover any one topic in very much depth. Think of this book of more of a survey of some AI methods out there.
AI topics are already very hard to understand, so I don't fault the author for that and appreciate the work he put into the book. However, the warehouse example in chapters 2/3 seems to be ill-explained. It seems like the author forgot to explain some assumptions about the application. I also wish there was more of a summary at the beginning explaining how everything ties together since the book contains many disparate subjects. The book doesn't have deep reinforcement learning algorithms like policy gradient and related methods, but that could be an entire book on its own.
I was disappointed by the blockchain section. The author did not describe or explain Bitcoin properly, and IBM's hyperledger is basically a timestamped list of entries as far as I understand (not a good or very useful blockchain, basically). I get the feeling the author probably adapted or expanded on some examples from IBM on using AI with hyperledger, but am not sure of this. One quote from the blockchain section that made me cringe was:
"Whether the goal is to mine bitcoins through blocks or use blocks for transactions,
artificial intelligence will enhance this innovation shortly."
All bitcoin blocks are composed of bitcoin transactions, as that's the entire point of bitcoin.
Overall, the book was decent, but I got the feeling it could be 3 or 4 books based on the range of topics discussed. AI books tend to be like that, however -- combining many subjects under one cover.
I am excited to further check out the chatbot sections because I haven't thoroughly looked at those. Again, you could easily write an entire book on chatbots, so there is probably a lot missing in the few chapters on chatbots.
I have looked through this book, and I have to say that I am disappointed. I wasn't quite sure what to expect from the title. Was it a beginner book? A cookbook? A book for experienced practitioners? After reviewing it, I still don't know.
What I Like:
This book has something that I hadn't seen in other Packt AI title: answers to the chapter exercises. That gave me an initial good feeling about the book, as did seeing that each chapter had a section for Further Reading, something that the more recent Packt titles appear to be doing.
Maybe the best thing I have found in this book is how each chapter is structured internally, the microstructure. The author organizes each chapter the same: textual comprehension through a use case, mathematical comprehension, example code, a summary, exercises, and further reading. I personally feel that this is a very structure to have.
What I Don't Like:
When looking over the TOC, I did not see a well organized structure, a macrostructure. The author starts with reinforcement learning, then talks about datasets, later talks about blockchain, further on the Internet of Things, a few chapters on chatbots, genetic algorithms, and finishes with quantum computing. In between some of these are chapters on CNNs, K-Means clustering, and a few topics. There is no natural flow and some of the topic choices, while interesting, don't really fit.
In chapter one, before getting into reinforcement learning, the author spends on section discussing what AI is, followed by his personal learning philosophy. To quote a section on 'Overcoming real-life issues using the three-step approach', "First, begin by understanding the subject as a subject matter expert. Then, write the analysis with words and mathematics to make sure your reasoning reflects the subject and, most of all, that the program will make sense in real life. Finally, in step 3, only write the code when you are sure about the whole project." In an agile world, this kind of programming gets left in the dust.
There are other bits and pieces within the book that I scratched my head over, such as suggesting an online encyclopedia article on the life of the inventor of a technique as further reading. One of the exercises, which are typically yes/no questions, is 'Can a human beat a chess engine? (Yes | No)'. And there are odd comments thrown in here and there, such as saying that anyone with a driver's license is an expert driver and so can use driving as an example for problems without consulting anyone else.
What I Would Like to See
More than anything else, I would like to see a book that is consistently about AI with a macrostructure that flows. To choose the right macrostructure, this book needs to decide what it is. If it's a reference, similar topics need to be within a group of chapters. If it's a beginner's learning book, then it needs to start with a simple topic and work its way toward the more complicated topics. I loved the proposed structure within the chapters (which unfortunately wasn't always followed clearly enough), but ingredients cooked perfectly don't make a god meal if they don't go together.
Overall, I give this book a 2.7 out of 5 stars, rounded up to 3. The author is clearly knowledgeable on the subject of AI, but they had trouble communicating it to their audience. I know that I will use this text to gain some important knowledge, but they are unfortunately the diamonds in the rough.