Since first proposed by Minsky and Papert, the spiral problem is well known
in neural networks. It receives much attention as a benchmark for various
learning algorithms. Unlike previous work that emphasizes learning, we appr
oach the problem from a different perspective. We point out that the spiral
problem is intrinsically connected to the inside-outside problem proposed
by Ullman. We propose a solution to both problems based on oscillatory corr
elation using a time-delay network. Our simulation results are qualitativel
y consistent with human performance, and we interpret human limitations in
terms of synchrony and time delays. As a special case, our network without
time delays can always distinguish these figures regardless of shape, posit
ion, size, and orientation.