Space Art
Galleries
Wallpaper
Star Trek

 

Computer Science
AI
NN.MDB
Free VB Code
 

Science Fiction
Stories

Free 3D Models
Ben's Scale Models
of Planetary Systems

Who I Am
And Who I'm Not

Contact Me

In
Computer Science
NN.MDB
The Database that Thinks

"I am endeavoring, ma'am, to create a mnemonic memory circuit, using stone knives and bearskins."

Spock , Star Trek
Episode "The City on the Edge of Forever"
1967

In short, I have created real, working Artificial Intelligence using nothing but an off-the-shelf database program. This is, I believe, the world's only Neural Network Simulator native to Microsoft Access.
 

It is a fully functional three-layer perceptron comprised entirely of VBA subs and functions, Access tables, and SQL queries.

Status: (Updated 2/2008)
Works, learns, proven. Training is a little slow (okay, very slow). Interface, testing and data I/O could be more "robust." Several things still NYI, and I have now taken the entire project in a new direction for my own NN experimentation. (see: Version 3)

READ MORE>>

Also In Space Art:
Wallpaper Images

Wide Screen 1650	Wide Screen 1650	1024 - 1280
1024-1280	1024 - 1280	1024 - 1280

“Probability Points the Other Way”   I was just a child when it started. I really didn't understand any of it. All I remember was Mother gathering all of us and hurrying us to the lightship. I asked why and she didn't answer. Then workers grabbed me a put me in one of those liquid-filled pods that was supposed to protect me. They closed the lid and it was dark. I was just a child.  I really didn't understand any of it.   I wish that I knew then that I would never see Mother again. I wish that I had known then that the World was about to end.  :Cydonian Tablet 295a2  Louis stopped reading the translation screen, “It looks like this one’s another biography, Henry,” he said into his helmet radio as his thickly gloved hands removed the millimeter thin stone tablet from the scanner, carefully putting it back on the dust covered shelf with the others. READ MORE>>

The Two Spirals Problem Solved Using a simple four-layer MLP and standard backprop (You're going to say I cheated.) While the Two-Spirals Problem may be (or actually, may not be) a valuable benchmark for neural network researchers working on new architectures, I believe that it much more valuable, and to a much larger number of people (those working on applied NN solutions), as an example of THE WRONG WAY to present data to a neural network. This paper is intended as a primer on how to evaluate, and manipulate, your dataset prior to building a neural network to improve or even guarantee your results.