My predictions is too noise?

[bizunow13]

Hello! I finally started testing my implementation on real data. I took a classic dataset, which reflects the amount of energy consumed by houses in a city.

On the graphs below, you can see the training stage at the very beginning, the identification of anomalies, but are there too many false “anomalies”?

First screen, from 0 to 1000 steps:

Second scree, from 2000 to 3000 steps:

Also you can see active and predicted columns here. It seems to me that too many columns are being predicted…

Sorry for the vague confusing question, I’m just trying to figure out if the predictions are valid and if there are too many false anomalies.

[aklandi]

What are the values of your parameters for encoder, SP, and TM?

[bizunow13]

Encoder parametrs:
Day of week: 100 bits, 21 active, periodic;
Time of day: 100 bits, 21 active, periodic;
Energy: 200 bits, 31 active, range is 0…70, not periodic.

SP - im use my own SP, his always provide 2% of active columns (2% is 50, total columns 2500). Maybe problem in my SP, now I can’t say for sure =(

TM - slightly different from vanila HTM TM, but I don’t think it matters. LEARNING_TRESHOLD is 5 and ACTIVATION_THRESHOLD is 10.

[sheiser1]

@bizunow13

LEARNING_TRESHOLD is 5 and ACTIVATION_THRESHOLD is 10

These values seem low to me, which could be causing too many predictions. It totally depends tho on columnCount and newSynapseCount. Would you share the whole parameters file?

Here’s the default used in the NuPIC hotgym example for comparison:

numenta/nupic-legacy/blob/master/examples/opf/clients/hotgym/anomaly/model_params.py