[strong_ai]

this doesn't look like a neural net to me. from NeuralNetwork.py

  from sklearn.neighbors import KNeighborsClassifier
  # Create a sperate neural network for each identifier
  for index in range(0, len(NaturalLanguageObject._Identifiers)):
       nn = KNeighborsClassifier()
       self._Networks.append(nn)

[ching_wow_ka]

So then it seems like the author of the code doesn't understand that "NN" means "Nearest Neighbors" and not "Neural Network"?

He mentions that he used sklearn's Neural Network libraries in his blog post, but sklearn doesn't have any aside from RBM.

[nl]

It is almost the perfect example of the "Danger Zone" in http://drewconway.com/zia/2013/3/26/the-data-science-venn-di...

[jacob_plaster]

I was confused with the difference between an SVM and a neural network. Easy mistake I guess. The whole goal of this project was for educational purposes, so im still happy with the outcome.

[stuxnet79]

OMG, how embarrassing for OP. This is what scares me about technical blogging. Messing up unknowingly in an area I'm not experienced in and getting scathing critiques from my fellow hackers. Keep your chin up OP and next time remember to do your homework. +1 for the effort anyways.

[strong_ai]

if you want to learn neural nets check out Karpathy's class (cs231n.github.io) and do the assignments. making a github repo and HN post about using neural networks is false self-advertising and illegitimatizes those of us who know what we are talking about.

[GFK_of_xmaspast]

"Easy mistake I guess"

What the hell.

[achompas]

Sorry to beat this issue to death, but this is not an easy mistake at all, even given only a cursory understanding of the field.

[lawlessone]

Should i be impressed that even though the author was not using the tool they thought then still got it to spit out something?

it must be a robust tool.

[nl]

I've glanced at the code now. You are absolutely correct.

Wow.

There's some good reasons to think this approach won't work at all. If I understand it correctly I think it is attempting to predict part of speech using previously observed values.

That's an interesting idea, and might be somewhat valuable as a feature to use in a text generator, but on its own won't be enough to ever generate sentences that make sense (because some specific sequences just don't make sense).