Performance of robust training algorithms for neural networks
Andreas Wendemuth · Journal of Physics A Mathematical and General · 1995
The performance of three recently presented training algorithms in neural networks is investigated. These algorithms are robust to infeasible problems, in which case an appropriate error function is minimized. In the infeasibility regime, simulations are performed and compared to recently published analytical work in one-step replica symmetry broken theory. A careful analysis explains insufficiencies in these analytic results. A new stability result in the infeasibility regime is derived and shown to match simulation data.