Optimality of Pocket Algorithm

Abstract

Many constructive methods use the pocket algorithm as a basic component in the training of multilayer perceptrons. This is mainly due to the good properties of the pocket algorithm confirmed by a proper convergence theorem which asserts its optimality. Unfortunately the original proof holds vacuously and does not ensure the asymptotical achievement of an… (More)
DOI: 10.1007/3-540-61510-5_87

Topics

  • Presentations referencing similar topics