Re:Google AI invents its own cryptographic algorithm
by bduerst on Friday October 28, 2016 @01:57PM
(#12818810)
>That simply depends on how the code was written
Not entirely true with ANNs built through deep learning. They can and often do exhibit unintended behaviors. When you start getting into a system of connected sub neural networks, the "why" can be obfuscated by the hidden layers.
Not entirely true with ANNs built through deep learning. They can and often do exhibit unintended behaviors. When you start getting into a system of connected sub neural networks, the "why" can be obfuscated by the hidden layers.