Hi Marcus, Please proofread my updated draft, on the neural programmer - interpreter.
I also need to verify the following fact: Am I correct in my understanding that the NPI approach can use programs it has already learned to create larger programs, while the DeepCoder approach does not have this functionality? As in DeepCoder uses a static library as the set of commands it can use, while we can easily update the command list (or program list) of the NPI? This is what I have based parts of my draft on, so if this fact is wrong, please explain why in a comment on the draft. Thanks, Hrishikesh Menon.
_______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
