Differences between revisions 4 and 5
Revision 4 as of 2004-06-22 14:12:53
Size: 363
Editor: wang
Comment:
Revision 5 as of 2004-06-22 17:00:39
Size: 635
Editor: ip68-4-10-228
Comment:
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
SpamAssassin's scores are assigned using a genetic algorithm. See RescoringProcess for details. SpamAssassin's scores were assigned using a genetic algorithm in versions up to 3.0.0. A good intro on genetic algorithms can be found here: http://lancet.mit.edu/~mbwall/presentations/IntroToGAs/
Line 3: Line 3:
A good intro on genetic algoirthmns can be found here: http://lancet.mit.edu/~mbwall/presentations/IntroToGAs/ Versions since 3.0.0 are now using a perceptron, written by Henry Stern, to perform the same task (but a lot faster); his program 'implements the "Stochastic Gradient Descent" method of
training a neural network. It uses a single perceptron with a logsig activation function and maps the weights to SpamAssassin score space.' See the file "masses/README.perceptron" for more details.
Line 5: Line 6:
See RescoringProcess for further details.
Line 6: Line 8:
''Yes, yes, and RescoringProcess points back here when it mentions the genetic algorithm...can anyone describe how the algorithm itself works?''

SpamAssassin's scores were assigned using a genetic algorithm in versions up to 3.0.0. A good intro on genetic algorithms can be found here: http://lancet.mit.edu/~mbwall/presentations/IntroToGAs/

Versions since 3.0.0 are now using a perceptron, written by Henry Stern, to perform the same task (but a lot faster); his program 'implements the "Stochastic Gradient Descent" method of training a neural network. It uses a single perceptron with a logsig activation function and maps the weights to SpamAssassin score space.' See the file "masses/README.perceptron" for more details.

See RescoringProcess for further details.

GeneticAlgorithm (last edited 2009-09-20 23:16:51 by localhost)