Classification: NPL Management Ltd - Commercial The science says that temperature should have an effect on the expansion of the bridge (tilt). We have made predictions without an encoder for temperature and with an encoder (added manually) and have come to the conclusion that the predictions for tilt were better with the encoder. (but only slightly)
Ø In fact, the more correlated a field is with the predicted field, the more likely that it is Ø unnecessary and will be left out. (This is the opposite of what happens in most machine Ø learning applications.) This is very interesting, why is this so? Unfortunately, the data file is absolutely massive (it takes over 10 hours for a small swarm to go over all the rows). I don't think we will have time to do a large swarm even over a smaller portion of the data. Thanks, Cavan From: nupic [mailto:[email protected]] On Behalf Of Matthew Taylor Sent: 21 August 2014 23:04 To: NuPIC general mailing list. Subject: Re: [nupic-discuss] Prediction of multiple time series for concrete bridge problem [NC] On Thu, Aug 21, 2014 at 2:24 PM, Subutai Ahmad <[email protected]> wrote: 3) You can actually force a specific field combination, using the "fixedFields" attribute. So you can add something like: "fixedFields": ["AWT_01","Tilt_01"], This will force swarm to only use the above two fields. It won't try any other field combinations, but it will optimize the other parameters. This is much faster since it has many fewer experiments to run. Wow, that is useful and something I didn't know. I want to update the https://github.com/numenta/nupic/wiki/Running-Swarms page with this, but I can't find any usage examples. I did find it in the JSON schema, however: https://github.com/numenta/nupic/blob/master/nupic/frameworks/opf/exp_generator/experimentDescriptionSchema.json#L303 --------- Matt Taylor OS Community Flag-Bearer Numenta -- If you have received this message in error, please notify us and remove it from your system. NPL Management Ltd cannot guarantee that the e-mail or any attachments are free from viruses. NPL Management Ltd is a company registered in England and Wales, number: 2937881 Registered office: Serco House | 16 Bartley Wood Business Park | Hook, Hampshire | UK | RG27 9UY
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
