Home ›

Neural network

Nguyen-Widrow and other Neural Network Weight/Threshold Initialization Methods

Submitted by jeffheaton on Mon, 05/03/2010 - 04:31
in

Neural networks learn by adjusting numeric values called
weights and thresholds.  A weight specifies how strong of a connection exists
between two neurons.  A threshold is a value, stored on each neuron that either
adds or subtracts from the incoming weights from other neurons.  Training is
the process by which these weights and thresholds are adjusted to cause the
neural network to produce useful results. 

Chapter 3: Using Activation Functions

Submitted by jeffheaton on Tue, 04/13/2010 - 18:33
in


Programming Neural Networks with Encog 2 in C#

Submitted by jeffheaton on Tue, 04/13/2010 - 16:32
in

Encog is an advanced neural network and bot programming framework. This book focuses on using Encog to create a variety of neural network architectures using the C# programming language. Neural network architectures such as feedforward/perceptrons, Hopfield, Elman, Jordan, Radial Basis Function, and Self Organizing maps are all demonstrated.

Initial GPU Graphics Acceleration Encog Results

Submitted by jeffheaton on Sun, 03/21/2010 - 17:59
in

Initial GPU(graphics processing unit) results are very good.

The mainline version of Encog .Net can now make use of the GPU for neural network calculation. No training yet, but this will come soon. I also plan to port this all to Java once I have the C# version working to my satisfaction.

EBooks for Encog C# and Java now on sale

Submitted by jeffheaton on Sun, 02/21/2010 - 10:28
in

The ebooks for Encog have been released. There is one for Java and another for C#. Both are on sale for $19.99. Paperback versions of each should be out in a few weeks.

Heaton Research's New(smaller) Home in SL

Submitted by jeffheaton on Sun, 01/10/2010 - 15:51
in

Given that we are now focusing more on neural network programming, than Second Life, we are scaling back our Second Life operations considerably. Heaton Research at one point had three islands in Second Life. We are dropping back to just a small area on "mainland" so that people can pick up the examples from our books. You can see the new Heaton Research home here.

You can access this area, and download any of our book examples, from the following URL.

http://slurl.com/secondlife/Venn/96/86/29

Syndicate content

Copyright 2005 - 2010 by Heaton Research, Inc.. Heaton Research™ and Encog™ are trademarks of Heaton Research. Click here for copyright and trademark information.