Re:Machine learning works spectacularly well, but mathematic...
by obsim on Friday December 04, 2015 @11:00AM
(#10677014)
A LSTM recurrent neural network was used to learn a learning algorithm: http://www.bioinf.jku.at/publications/older/1504.pdf
Maybe start with a minimal implementation 'bootstrap protozoa' that can evolve to highly complicated forms.
Then realised that since Machine Learning processes takes a long time that would take forever making auto evolving computer life forms a long way away.
Although if it were possible, in the same way we became sentient based on very simple inputs, that could also mean computers, with a sufficiently complex process, could too...