Re:A Brief Overview of Deep Learning
by Houshalter on Thursday February 12, 2015 @12:57PM
(#9040137)
Neural networks are universal function approximators, not Turing machines. They can theoretically learn any series of "if...then..." functions with enough neurons. But there are a lot of functions they can't represent very efficiently or without absurdly large numbers of neurons and training data.
[ Parent
| on HN ]
Yes, but computation can be performed with a function approximator where each iteration is a function `f :: (state, input) -> (state', output)`. This is the basis of an architecture called a 'neural turing machine' (http://arxiv.org/abs/1410.5401) and it is, indeed, Turing complete and can be trained through standard neural network training algorithms to perform arbitrary computations.