Back to my homepage.
Abstract: This is a Masters thesis in German. Ackley, Hinton and Sejnowski introduced a very interesting and versatile learning algorithm for the Boltzmann machine (BM). However it is difficult to decide when to stop the learning procedure. Experiments have shown that the BM may destroy previously achieved results when the learning proces s is executed for too long. We introduce a new quantity, the conditional divergence, measuring the learning success f or the inputs of the data set. To demonstrate its use, some experiments are presented, based on the Encoder Problem.
Back to my homepage.