Bayesian Parameter Optimization with SVM

Haven't been updating for a while and KNIME was upgraded to 4.0.0!! Must play with this then. So gonna play first with Bayesian Optimization new in 4.0.0

f:id:hateknime:20190803135954p:plain

Parameter Optimization placement in the workflow is the same but I'm playing with SVM this time because the paraters are more diverse and hence a nice example for Bayesian Optimization.

Math Formula is changing the values to the power of 2 so that paramters are spread out.

 

f:id:hateknime:20190803140005p:plain

Then set the paramters in the loop start menu and run!!

 

f:id:hateknime:20190803140015p:plain

and here's the reuslts. pretty cool and definitely faster but gives a good result.KNIME is so much fun. gonna play with SHAP too now.