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.
CITATION STYLE
Minsky, M. (2014). Evolutionary artificial neural networks. Adaptation, Learning, and Optimization, 15, 187–230. https://doi.org/10.1007/978-3-642-37846-1_7
Mendeley helps you to discover research relevant for your work.