Neural Network Toplogy & Optimize Neural Network

Hello, i would like to optimize a neural net using Genetic Algorithms, there is a operator named Optimize Parameters (Evolucionary) where i can use genetic algorithms approaches to optimize the neural net, but it wont let me use genetic algorithms to determine the best number of hidden layers and their respective values. Is there a way I can optimize my neural net with genetic algorithms approaches but optimizing the number of hidden layers and values?
Thanks.
Best Answer
-
This has been discussed and successfully closed here: http://community.rapidminer.com/t5/RapidMiner-Studio/Neural-Network-Toplogy-amp-Optimize-Parameters-Grid/m-p/31407#U31407
3
Answers
-
With the standard RapidMiner Neural Network I haven't yet found a way to do this. You can download our free DL4J extension which will work with the optimize parameter operators.
Please note however, that it is still early Beta so it might throw an error for some parameter settings so make sure you keep an eye on it. We're working on this.
John
RapidMiner China - RapidMiner sales & consulting in China.
1 -
I knew that i found a way together with @MariusHelf to do this. But i do not remember how anymore..
~Martin
0 -
This has been discussed and successfully closed here: http://community.rapidminer.com/t5/RapidMiner-Studio/Neural-Network-Toplogy-amp-Optimize-Parameters-Grid/m-p/31407#U31407
3