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 architec...

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.

quote by Marvin Minsky
Submitted by Lucian Velea
Vote! | Copy!