I see there is a Model configuration parameter tmImplementation with two options, cpp and tm_cpp. Is there a good writeup discussing when to use which? Also, is one better for time series anomaly detection?
Any insight is greatly appreciated–thanks!
tm_cpp are the newer Temporal Memory algorithm (python and cpp), which is more biologically pure. The other implementations are the BacktrackingTM (both python and cpp), which is performs better for anomaly detection tasks because of extra bells and whistles added specifically for anomaly detection tasks.
Sounds cool, thanks Matt!
FYI: The backtracking version of the TM is not being further developed. Current research uses
TemporalMemory or extensions of it.