Are we capturing these feed requests in a central place so that the features worked on for NuPIC 2.0 are a reflection of the requests that tend to come up from the community?
Cheers, David On Wed, Oct 7, 2015 at 6:04 PM, Matthew Taylor <[email protected]> wrote: > Jonathan, > > Sorry it has taken so long for us to get back to you about this. Please > watch this video: https://www.youtube.com/watch?v=XK5Dd8fGO2w > > Regards, > > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > On Wed, Sep 30, 2015 at 7:07 PM, Jonathan Mackenzie <[email protected]> > wrote: > >> Hi, >> >> I want to set up my model params so that all inputs are encoded and used >> as part of the anomaly detection. After running my swarm, it decided to >> only encode the sensor that is used for the prediction (it would also be >> nice if I could make predictions for all sensors). Also, is the timestamp >> field correctly encoded? The prediction field is chosen because it's the >> most highly used sensor. >> >> My swarm config is here along with the resultant model params: >> https://gist.github.com/JonnoFTW/b0a81a67a9a09e24c3b2 >> >> How do I configure my swarm so that it encodes all relevant fields if I >> want anomaly detection (and possibly predictions) across all sensors? >> >> -- >> *Jonathan Mackenzie* >> BEng (Software) Hons >> PhD Candidate, Flinders University >> > > -- *With kind regards,* David Ray Java Solutions Architect *Cortical.io <http://cortical.io/>* Sponsor of: HTM.java <https://github.com/numenta/htm.java> [email protected] http://cortical.io
