Generally, a machine learning system would only make a single prediction among available classes (classification) or predict a single real valued number (regression) based on the given set of features for an instance.
Would it be possible to train a system in WEKA to make two predictions for a given sample?
Although this question could be useful in many angles. A particular use case I would like to use this functionality is predicting an (x,y) coordinate given a set of features of an image. In here, x and y are the two variables to be predicted.
Does WEKA tool have the ability to do this?
You can have two approaches, first it to consider each one of your outputs once with the whole inputs, and the other is to use classifier, which can have multiple outputs, which is basically the ability of any classifier with proper modeling. Neural Nets and KNN are two example of the classifiers having this ability and easy to use.
Hi
Yes it is possible.
You can use different algorithms together on the same dataset and get different outputs.
You need to chose suitable algorithms. You need to use knowledge flow or Experimenter for the same.
You can execute various algorithms in parallel.
Thank you.
What you want to do is normally referred to as multivariate regression. Whether this is possible in WEKA I do not know, but it is a pretty standard feature of any ML tool. On one forum I just saw that "Unfortunately, Weka does not support more than one dependent variable in the same model". If that is the case then your only option is to make separate models for each of your output variables (or use something different from WEKA ....)
The term is multivariate multiple regression.
You can find a tutorial about how to form it in R, here: http://www.uni-kiel.de/psychologie/rexrepos/posts/multRegression.html
MEKA an extension of WEKA is endowed with such capability. It is free you can download i
- Badges
- Science topic