Re:Mark Cuban on Why You Need to Study Artificial Intelligence
by Eridrus on Wednesday February 08, 2017 @01:28PM
(#13600671)
To say something in defence of the deep learning religion: it's a very flexible framework for expressing lots of different ideas and the ability to train all those ideas jointly if you can frame them in terms of SGD updates is very appealing.
And even if you don't want to use SGD to fit your model, the deep learning machinery can be reused for other things like bayesian inference, eg PyMC3 and Edward are built on Theano/TensorFlow respectively.
There have even been papers showing differentiable trees integrated into the deep learning framework. There is work on how to input graphs.
Maybe this is just my own desire for unifying frameworks shining through, but joint training seems to have real benefits and feature learning has clearly had a large impact on reinforcement learning.
Maybe it's not the best tool for day to day data science work, but that tends towards what tools are accessible and good enough, rather than what is best.
And even if you don't want to use SGD to fit your model, the deep learning machinery can be reused for other things like bayesian inference, eg PyMC3 and Edward are built on Theano/TensorFlow respectively.
There have even been papers showing differentiable trees integrated into the deep learning framework. There is work on how to input graphs.
Maybe this is just my own desire for unifying frameworks shining through, but joint training seems to have real benefits and feature learning has clearly had a large impact on reinforcement learning.
Maybe it's not the best tool for day to day data science work, but that tends towards what tools are accessible and good enough, rather than what is best.