Hi folks, Just for inform that I wrote a spelling checker that infer solutions based on context using CLA algorithms. It was written in C# and use a CLA version nicely provided by my fellow Michael Ferrier at OpenHTM.
I created my own engine to encode words to HTM and decode the the likely words according to context. This project was created for my Master thesis, and I think it could be breakthough related to extending the Nupic examples for NLP. Although it still present accuracy and speed less than N-Gram approach, yet it is able to provide good corrections successly. My aim is replace the current engine to Numenta engine probally using bindings for C# or then converting the entire project to Python.. I believe the Numenta engine is mature enough to improve accuracy and speed. This done, hopefully I will present it in hackatheon. I'll let you know as soon as I finish this job. :-) Best regards, -- David Ragazzi OS Community Commiter 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."
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
