Perceptron in Lisp

Perceptron is the simplest artificial neural network, a “Hello World” of neural networks.

It is in every ANN package, and there are many implementations of it in different languages in the Internet.

Here’s my version in Lisp: link. (Link to the folder where additional files are: link)


(load "perceptron")


The parameters are specified in the file parameters.txt

The program outputs the final weights of the perceptron.

I also uploaded two training sets to the same folder: one for and and another for or logical functions.

Testing for and:

Testing for or:

The program allows to specify the activation function (in the file activation-functions.lisp), the type of a combiner of weights and inputs to the neuron (it doesn’t have to be just a linear combination of them; file: combiners.lisp) and learning rules (learning-rules.lisp)

Right now, I only wrote the usual delta rule and a linear combiner. Will try to add more later.

I’ll be thankful for suggestions.

Published in: on 19/11/2012 at 00:38  Leave a Comment  

The URI to TrackBack this entry is:

RSS feed for comments on this post.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: