I doubt you will run into anyone who has done both? :-) So the comparison may be hard to come by. I found my porting experience very instructive - but it may be a bit "over kill" to port an entire framework, you might want to simply port the major algorithms?
As far the comparison between starting from scratch and porting, I can just say that porting worked for me - and in the end I'd bet you want to more so attain an affinity with the existing implementation more than the white paper. Besides, the white paper is obsolete now and doesn't reflect the current TemporalMemory implementation, no? On Thu, Apr 16, 2015 at 12:27 PM, Jeff Fohl <[email protected]> wrote: > I am interested in learning the HTM algorithms at a deeper level by > writing my own implementation. The language I am currently work with most > frequently is Javascript, so I was planning on doing my implementation in > that language. > > My question for those who have gone this route already is: if the primary > goal of the exercise is a deeper understanding of the algorithms, is it > best to start from scratch, implementing the pseudocode as described in the > white paper, or is porting an existing implementation - such as htm.java > more fruitful? > > - Jeff > -- *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
