Examples Using the Perceptron Learning Rule and Excel.


The Perceptron Learning rule can be implemented easily using Excel. The User interface is not, perhaps, quite as nice as it could be made in Java or C++, but (given a working knowledge of Excel) you can see exactly what is going on.

I have produced a spreadsheet which learns the network which will compute the logical AND of two inputs, where 1 is TRUE and 0 is FALSE. (There are sometimes problems making the  Netscape Browser start up Excel from this link. Ideas? One way of getting the document using Netscape is to right-click on the word spreadsheet above, then save the file, and open it with Excel.) (It seems to work OK using Internet Explorer, leastwise in 1A11).

If you can't get Netscape to download the perceptron file (and I can't either, today), it IS available by anonymous ftp. The following dialogue does work (you can  get it using the browser too, starting from URL
ftp://ftp.cs.stir.ac.uk)

ftp ftp.cs.stir.ac.uk

(then login as anonymous)

cd pub/staff/lss
binary
get perceptron.XLS

I have no idea why Netscape won't start up Excel. Oddly enough it occasionally works, and that seems even odder!

Once you have the spreadsheet program, it should be a simple matter to alter it to make it learn different 2-input predicates, such as NOR, NAND and OR.

Back to Biologically-inspired Computing Home page
email lss    last updated 5 November 1999