Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

The single-layer perceptron, introduced by Rosenblatt in 1958, is one of the earliest and simplest neural network models. However, it incapable classifying linearly inseparable patterns. A new era research started 1986, when backpropagation (BP) algorithm was rediscovered for training multilayer perceptron (MLP) model. An MLP with a large number hidden nodes can function as universal approximator. To date, model most fundamental important It also investigated Even this AI or deep learning era, still among few used Numerous results have been obtained past three decades. This survey paper gives comprehensive state-of-the-art introduction to model, emphasis on learning, generalization, selection fault tolerance. role described. provides concluding covers all major achievements seven serves tutorial learning.