The effectiveness and efficiency of a Hopfield-style neural network re
cently proposed by Takefuji and Lee for the knight's tour problem on a
n nxn board are compared and contrasted with standard algorithmic tech
niques using a combination of experimental and theoretical analysis. E
xperiments indicate that the neural network has poor performance when
implemented on a conventional computer, and it is further argued that
it is unlikely to improve significantly when implemented in parallel.