News for hackers. Stuff that matters.

A comment on A landmark 2012 paper transformed how software recognizes images. Parent comment

Re:A landmark 2012 paper transformed how software recognizes... by bkanber on Wednesday January 02, 2019 @04:51PM (#18810592)
Sure, lots! We've made lots of progress just in the last decade or two. LSTM, recurrent, and convolutional nets. Slightly older (late 90's), but I think Random Forests were a pretty significant breakthrough.

Another huge one is Paul Graham's own work using Naive Bayes to filter spam.

[ Parent | on HN ]
Re:A landmark 2012 paper transformed how software recognizes... by p1esk on Wednesday January 02, 2019 @05:06PM (#18810737)
Both convolutional and recurrent architectures were developed in late 80s. LSTM (improved RNN) was published in 1997.
[ Parent | on HN ]