English: A three layer Perceptron net capable of calculating XOR. The numbers within the perceptrons represent each perceptrons' explicit threshold. The numbers that annotate arrows represent the weight of the inputs. This net assumes that if the threshold is not reached, zero (not -1) is output. Note that the bottom layer of inputs is not always considered a real perceptron layer.
This work has been released into the public domain by its author, Robert.ensor at English Wikipedia. This applies worldwide. In some countries this may not be legally possible; if so: Robert.ensor grants anyone the right to use this work for any purpose, without any conditions, unless such conditions are required by law.Public domainPublic domainfalsefalse
Original upload log
The original description page was here. All following user names refer to en.wikipedia.
2006-07-15 00:45 Joerite 279×277× (16529 bytes) Made better {{PD-retouched-user|Joerite}}
2006-07-15 00:42 Joerite 790×714× (32375 bytes) Made better {{PD-retouched-user|Joerite}}
2005-04-15 23:13 BrokenSegue 418×345× (27586 bytes) center the key
2004-11-05 09:20 Robert.ensor 418×345× (27058 bytes) A perceptron net capable of calculating XOR. {{PD}} I created it myself with Visio. Email me if you want the VSD
Captions
Add a one-line explanation of what this file represents
It's included in the article Artificial Neural Network in the English version of Wikipedia. Description: A two-layer neural network capable of calculating XOR.