News for hackers. Stuff that matters.
Re:How Google Translate squeezes deep learning onto a phone by sushirain on Wednesday July 29, 2015 @03:29PM (#9971026)
They are effective because:

- They use more parameters (and fewer computations per parameter.)

- They are hierarchical (convolutions are apparently useful at different levels of abstraction of data).

- They are distributed (word2vec, thought-vectors). Not restricted to a small set of artificial classes such as parts-of-speech or parts of visual objects.

- They are recurrent (RNN).

etc.

Re:How Google Translate squeezes deep learning onto a phone by kylebgorman on Wednesday July 29, 2015 @08:53PM (#9972661)
word2vec isn't "deep" in the relevant sense. The both skipgram and CBOW forms have a single hidden layer.