This book presents output sensitivity of the most popular feedforward neural network, MLPs (Multi-Layer Perceptrons), with respect to input and weight perturbations. Based on the structural features of MLPs, a bottom-up approach is proposed, in which the sensitivity of a neuron is considered first, then is that of a layer, and finally an entire network. Besides, applications of the sensitivity are also discussed.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.