Good idea David.  That makes me think, do we have a standard benchmark defined 
to test an HTM implementation against?  I think that it would be extremely 
helpful to have a set benchmarks defined so we could compare changes to the 
encoders, new sensorimotor algorithm, or different implementations.  I think 
this benchmark would need to look at several different aspects of the 
performance, such as:
  - how long does it take to train
  - how accurate is it after 1x the training data, 10x, 100x, ...
  - how well does it detect anomalies

Then we would need to come up with a few standard sets of data.  Some that HTM 
is traditionally good at like hotgym, and some that it is not, like sine wave.  
This would allow us to objectively compare different code sets and see if 
anything is improved.

Does anything like this currently exist?  Other thoughts or comments?

Matt

On Jan 6, 2015, at 5:00 AM, David Ragazzi <[email protected]> wrote:

> Hi guys,
> 
> It is known that many here have implemented their own versions of HTM.  Some 
> implementations have features that even Nupic implementation still doesn't 
> have. So I think is a healthy discussion you share the description of 
> implementations, and who knows we take the best from each one and replicate 
> these features on Nupic (if biologically plausible, of course). This would 
> accelerate the process of make Nupic closer to brain.
> 
> Again, it would be interesting heard implementations that really have 
> something else than Nupic: I mean cognitive features like better 
> inference/learning, motor integration, or even performance improvements like 
> parallelism and others, and that are biologically designed (based on cells 
> archicteture, not on mathematical rules).
> 
> Looking forward for heard you,
> 
> Cheers,
> -- 
> David Ragazzi
> MSc in Sofware Engineer (University of Liverpool)
> OS Community Commiter at Numenta.org
> --
> "I think James Connolly, the Irish revolutionary, is right when he says that 
> the only prophets are those who make their future. So we're not anticipating, 
> we're working for it."

Reply via email to