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.

This collection had a strong influence on modern computational linguistics. Edited collection of essays about robotics with Introduction and Postscript by Minsky. The theory attempts to explain how what we call intelligence could be a product of the interaction of non-intelligent parts.