Re:AI, Deep Learning, and Machine Learning: A Primer [video]
by gavanwoolery on Saturday June 11, 2016 @11:57AM
(#11883901)
Yep - also we have a large tendency to use feedforward NNs right now, but I have a sneaking suspicion that the future lies in something closer to recurrent NNs. Or probably something more complex, like automata-ish properties (IIRC there is also some NN that uses Turing-like devices).
Re:AI, Deep Learning, and Machine Learning: A Primer [video]
by eli_gottlieb on Saturday June 11, 2016 @09:52PM
(#11886272)
Nah. If we want properly humanlike AI software, we're going to have to find a way to make inference in probabilistic programs a lot faster.
Hopfield nets for example provide associative memory.
It may not all be groundbreakingly efficient, but very worthwhile.