If you just have a single problem to solve then fine go ahead and use a neural network. But if you want to do science and understand how to choose architectures or how to go to a new problem you have to understand what different architectures can and cannot do.
I'm up here in Cleveland tonight and there are a lot of folks who are concerned about it. Twenty-five percent of the people up here get their health care through religious organizations and so that religious freedom issue is very important to them.