Hi friends of NuPIC! I am a researcher currently working on an experimental project applying > NuPIC to a large dataset for multivariate time series anomaly detection and > I have been running into various difficulties getting it to work. I hope > this is a good forum to share these questions and see if anyone has > experienced similar problems or can offer any advice. Thanks in advance!
The swarming process chooses which fields are relevant for predicting the target field and in my datasets will often ignore most of my fields because it thinks that it does not contribute to predicting the target field. For prediction it makes sense, but in my case I am interested in anomaly detection over all my fields. Is there a way to specify that I want all fields included (e.g., in the json?). One workaround that I can think of is to run the swarming process once for each field set as the target field. This guarantees that it will be included in sensorParams. Then manually mash together the sensorParams : encoders section. Would this work? Thanks, Ritchie Lee Research Engineer Carnegie Mellon University-Silicon Valley NASA Ames Research Center Bldg 23, Rm 115 Moffett Field, CA 94035 (650) 335-2847
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
