Meta construction capabilities


I am currently considering Knime as the base for a meta-learning assistant prototype I intend to develop, but before committing myself to a thorough exploration of the documentation and learning about eclipse development (which would both be quite time consuming), I would appreciate some insight regarding the feasibility of such prototype within Knime framework.

The main aim of the prototype I intend to develop is to allow efficient use of data mining and machine learning algorithm by non experts. Concretely, I wish as a first step to be able to give the user a workflow answering his modelling need, that I elicit from his dataset and expression of his need. In order to perform this elicitation, I intend to run a process that implies designing and executing machine learning workflows on his data.

My question is thus the following : is it possible from within the Knime framework (or else from an above "supervising" framework) to automatically define and execute learning workflows ?

Hi Will,

this is exactly what KNIME is for. :-)

We also offer a webserver, with which you are able to hide the workflows from the user and they will only see the input parameters you allow them to see.

If you want to learn more, you could also join one of our trainings. Or check out the Learning Hub and our Youtube Videos.

Best, Iris

Hello Iris,

First, thanks for answering me :-)

I went through the available documentation and videos to see if I could find any example of meta-construction, but the best I found is that it appears possible to automatically execute a previously defined workflow over new data. 

I'm sorry to ask again, but I really need to be sure and I couldn't find any actual reference to such functionnality... Is it possible, from within knime or above, to "script" the definition of a workflow ? Where could I write a script/program that would select nodes and organise them into a workflow, configure them, execute the workflow and use its results ? Is there any documentation on that topic ?

Thanks again, and sorry if I overlooked anything,

All the best,