Current Books
These are the books that I currently support and keep up to date.
Applications of Deep Neural Networks with Keras
This book contains a complete course on deep neural work applications with Keras. I provide YouTube videos and a GitHub repository of all code and text for this book. Topics covered include tabular data, images, GANs, reinforcement learning, transformers, and natural language processing. All examples are in the Python programming language.
This book contains a complete course on deep neural work applications with Keras. I provide YouTube videos and a GitHub repository of all code and text for this book. Topics covered include tabular data, images, GANs, reinforcement learning, transformers, and natural language processing. All examples are in the Python programming language.
Artificial Intelligence for Humans
My Artificial Intelligence for Humans (AIFH) focused on building algorithms from scratch in languages such as Java, C#, Python, and R. Volumes 1 and 3 have evolved into my current Applications of Deep Neural Networks for Kindle.
Artificial Intelligence for Humans, Vol 1: Fundamental Algorithms
A great building requires a strong foundation. This book teaches basic Artificial Intelligence algorithms such as dimensionality, distance metrics, clustering, error calculation, hill climbing, Nelder Mead, and linear regression. These are not just foundational algorithms for the rest of the series, but are very useful in their own right. The book explains all algorithms using actual numeric calculations that you can perform yourself. Artificial Intelligence for Humans is a book series meant to teach AI to those without an extensive mathematical background. The reader needs only a knowledge of basic college algebra or computer programming?anything more complicated than that is thoroughly explained. Every chapter also includes a programming example. Examples are currently provided in Java, C#, and R.
A great building requires a strong foundation. This book teaches basic Artificial Intelligence algorithms such as dimensionality, distance metrics, clustering, error calculation, hill climbing, Nelder Mead, and linear regression. These are not just foundational algorithms for the rest of the series, but are very useful in their own right. The book explains all algorithms using actual numeric calculations that you can perform yourself. Artificial Intelligence for Humans is a book series meant to teach AI to those without an extensive mathematical background. The reader needs only a knowledge of basic college algebra or computer programming?anything more complicated than that is thoroughly explained. Every chapter also includes a programming example. Examples are currently provided in Java, C#, and R.
Artificial Intelligence for Humans, Vol 2: Nature-Inspired Algorithms
Nature can be a great source of inspiration for artificial intelligence algorithms because its technology is considerably more advanced than our own. Among its wonders are strong AI, nanotechnology, and advanced robotics. Nature can therefore serve as a guide for real-life problem solving. In this book, you will encounter algorithms influenced by ants, bees, genomes, birds, and cells that provide practical methods for many types of AI situations. Although nature is the muse behind the methods, we are not duplicating its exact processes. The complex behaviors in nature merely provide inspiration in our quest to gain new insights about data.
Nature can be a great source of inspiration for artificial intelligence algorithms because its technology is considerably more advanced than our own. Among its wonders are strong AI, nanotechnology, and advanced robotics. Nature can therefore serve as a guide for real-life problem solving. In this book, you will encounter algorithms influenced by ants, bees, genomes, birds, and cells that provide practical methods for many types of AI situations. Although nature is the muse behind the methods, we are not duplicating its exact processes. The complex behaviors in nature merely provide inspiration in our quest to gain new insights about data.
Artificial Intelligence for Humans, Vol 3: Deep Learning and Neural Networks
Neural networks have been a mainstay of artificial intelligence since its earliest days. Now, exciting new technologies such as deep learning and convolution are taking neural networks in bold new directions. In this book, we will demonstrate the neural networks in a variety of real-world tasks such as image recognition and data science. We examine current neural network technologies, including ReLU activation, stochastic gradient descent, cross-entropy, regularization, dropout, and visualization.
Neural networks have been a mainstay of artificial intelligence since its earliest days. Now, exciting new technologies such as deep learning and convolution are taking neural networks in bold new directions. In this book, we will demonstrate the neural networks in a variety of real-world tasks such as image recognition and data science. We examine current neural network technologies, including ReLU activation, stochastic gradient descent, cross-entropy, regularization, dropout, and visualization.
Books About Encog
Encog is a open source machine learning framework that I created for Java and C#. I have a book on Encog for each language. These books can be downloaded free; however, I also sell paperback and Kindle versions.
Programming Neural Networks with Encog3 in Java, 2nd Edition
Encog is an advanced Machine Learning Framework for Java, C# and Silverlight. This book focuses on using the neural network capabilities of Encog with the Java programming language. This book begins with an introduction to the kinds of tasks neural networks are suited towards. The reader is shown how to use classification, regression and clustering to gain new insights into data. Neural network architectures such as feedforward, self organizing maps, NEAT, and recurrent neural networks are introduced. This book also covers advanced neural network training techniques such as back propagation, quick propagation, resilient propagation, Levenberg Marquardt, genetic training and simulated annealing. Real world problems such as financial prediction, classifiction and image processing are introduced.
Encog is an advanced Machine Learning Framework for Java, C# and Silverlight. This book focuses on using the neural network capabilities of Encog with the Java programming language. This book begins with an introduction to the kinds of tasks neural networks are suited towards. The reader is shown how to use classification, regression and clustering to gain new insights into data. Neural network architectures such as feedforward, self organizing maps, NEAT, and recurrent neural networks are introduced. This book also covers advanced neural network training techniques such as back propagation, quick propagation, resilient propagation, Levenberg Marquardt, genetic training and simulated annealing. Real world problems such as financial prediction, classifiction and image processing are introduced.
Programming Neural Networks with Encog3 in C#, 2nd Edition
Encog is an advanced Machine Learning Framework for Java, C# and Silverlight. This book focuses on using the neural network capabilities of Encog with the Java programming language. This book begins with an introduction to the kinds of tasks neural networks are suited towards. The reader is shown how to use classification, regression and clustering to gain new insights into data. Neural network architectures such as feedforward, self organizing maps, NEAT, and recurrent neural networks are introduced. This book also covers advanced neural network training techniques such as back propagation, quick propagation, resilient propagation, Levenberg Marquardt, genetic training and simulated annealing. Real world problems such as financial prediction, classifiction and image processing are introduced.
Encog is an advanced Machine Learning Framework for Java, C# and Silverlight. This book focuses on using the neural network capabilities of Encog with the Java programming language. This book begins with an introduction to the kinds of tasks neural networks are suited towards. The reader is shown how to use classification, regression and clustering to gain new insights into data. Neural network architectures such as feedforward, self organizing maps, NEAT, and recurrent neural networks are introduced. This book also covers advanced neural network training techniques such as back propagation, quick propagation, resilient propagation, Levenberg Marquardt, genetic training and simulated annealing. Real world problems such as financial prediction, classifiction and image processing are introduced.
Older Books
These are older books covering such topics as building pre-deep learning neural networks from scratch, Second Life, webscraping (before API's became common), building computers, and even introductory Java programming. I also documented my open-source Encog machine learning library for Java and C#.- 1998, December - Sams Teach Yourself Visual C++ 6 in 21 Days
- 2002, February - Programming Spiders, Bots, and Aggregators
- 2002, September - Jstl-Jsp Standard Tag Library Kick Start
- 2003, June - BEA WebLogic Server 8 For Dummies
- 2005, November - Introduction to Neural Networks with Java [Download]
- 2006, May - Java for the Beginning Programmer [Download]
- 2006, June - Build a Computer from Scratch [Download]
- 2007, April - HTTP Programming Recipes for C# [Download]
- 2007, April - HTTP Programming Recipes for Java Bots [Download]
- 2007, July - Scripting Recipes for Second Life [Download]
- 2007, September - Introduction to Textures, Animation Audio and Sculpting in Second Life [Download]
- 2007, December - Introduction to Linden Scripting Language for Second Life [Download]
- 2008, October - Introduction to Neural Networks with Java, 2nd Edition [Download]
- 2008, October - Introduction to Neural Networks for C#, 2nd Edition [Download]
- 2010, March - Programming Neural Networks with Encog 2 in Java [Download]
- 2010, March - Programming Neural Networks with Encog 2 in C# [Download]