Artificial Intelligence

jeffheaton's picture

A Non-Mathematical Introduction to Using Neural Networks

The goal of this article is to help you understand what a neural network is, and how it is used. Most people, even non-programmers, have heard of neural networks. There are many science fiction overtones associated with them. And like many things, sci-fi writers have created a vast, but somewhat inaccurate, public idea of what a neural network is.

jeffheaton's picture

Four Part Encog Silverlight Demo Released

Would you like to see Encog Silverlight in action? Silverlight works quite a bit like flash. Except you can program it in C#, without having to learn Flash. There is a version of Encog for Silverlight. You can see several examples, in full GUI, here.

http://www.heatonresearch.com/encog/benchmark.html

jeffheaton's picture

Encog DotNet 1.1 has been released

We just released version 1.1 of Encog for DotNet. This also includes a Workbench that allowed editing of Encog datafiles. This is a major update to the Encog Neural Network and Bot framework. v1.1 adds the Encog workbench, which is a GUI tool that can be used to edit the .EG files that Encog uses to save neural networks and training data. The workbench can be used to construct all neural network types that Encog supports, such as Hopfield, Feedforward, and Self Organizing Maps. Training can also be performed using the workbench.

jeffheaton's picture

Introduction to Neural Networks for C#, Second Edition

Introduction to Neural Networks with C#, Second Edition, introduces the C# programmer to the world of Neural Networks and Artificial Intelligence. Neural network architectures, such as the feedforward, Hopfield, and self-organizing map architectures are discussed. Training techniques, such as backpropagation, genetic algorithms and simulated annealing are also introduced. Practical examples are given for each neural network. Examples include the traveling salesman problem, handwriting recognition, financial prediction, game strategy, mathematical functions, and Internet bots.

jeffheaton's picture

Encog 1.0 for Java Released

Encog 1.0 for Java has been released. Encog 1.0 for C# will be released soon, and is currently in the works. For now, Encog 0.5 is the current C# release. The following is a list of features that were implemented in Encog 1.0.

  • All Neural networks should implement the Network interface
  • Package structure reorg
  • Allow the three neural networks to be persisted in an XML format
  • Unify the three neural network types into a single solution
  • Add an image based data source
  • Add a CSV based data source
jeffheaton's picture

Introduction to Neural Networks for Java, Second Edition

Introduction to Neural Networks with Java, Second Edition, introduces the Java programmer to the world of Neural Networks and Artificial Intelligence. Neural network architectures, such as the feedforward, Hopfield, and self-organizing map architectures are discussed. Training techniques, such as backpropagation, genetic algorithms and simulated annealing are also introduced. Practical examples are given for each neural network. Examples include the traveling salesman problem, handwriting recognition, financial prediction, game strategy, mathematical functions, and Internet bots.

jeffheaton's picture

Introduction to Neural Networks with Java, 2nd Edition EBook Available


Introduction to Neural Networks with Java, Second Edition
is now available for purchase
E-Book form! You can also download all examples from this book. We will be posting about
half of it online soon. The book will go off to the printer on Monday, and will show up
on Amazon(and the others) in paperback form within a few weeks. The C# neural network
book is nearly complete. It should come out sometime in October, 2008.

jeffheaton's picture

Encog for C# Released

Version 0.5 of Encog-C# has been released. A Java version is also available. Encog is a framework that includes neural networks, as well as HTTP bots and spiders. Heaton Research has released books on these two very interesting topics. We will soon be updating our Java neural network book, as well as adding a C# neural network book. The books are meant to introduce the topics of bots and neural networks. We are now combining the code from the books into an open source framework so that the code can be extended and moved into more advanced areas than the introductory topics of the books.

jeffheaton's picture

Two New Neural Network Books Coming Soon

I am nearing the final stages of two new books. Introduction to Neural Networks for Java and Introduction to Neural Networks for C#. The Java book is the Second Edition to the original "Introduction to Neural Networks with Java". This is a considerable update to the original text. The covers for the two new books can be seen below. The Java book is expected to be out in September,2008. The C# book by January,2009. More information on these two books will be posted in the coming weeks.

jeffheaton's picture

What is Mindstorm NXT

This is the first of several articles about Lego Mindstorm NXT. This article introduces you to the parts included with the Mindstorm NXT kit. You will see what is included and how they work together.

Syndicate content

Copyright 2005 - 2012 by Heaton Research, Inc.. Heaton Research™ and Encog™ are trademarks of Heaton Research. Click here for copyright, license and trademark information.