Portal de Periódicos da CAPES

Neural Networks and Deep Learning

2015; Springer Nature; Linguagem: Inglês

10.1016/b978-0-12-801522-3.00018-5

2730-9916

Sergios Theodoridis,

Face and Expression Recognition

This chapter deals with neural networks (NN), starting from the early days of the perceptron and perceptron rule, then moves on to review multilayer feed-forward neural networks and the backpropagation algorithm. The drawbacks of training NN with many layers, via the backpropagation algorithm, are discussed together with the advantages that one would expect to obtain if such networks could be trained efficiently. Restricted Boltzmann machines (RBM) are then discussed and the contrastive divergence algorithm is presented as the vehicle to pre-train deep/many layer NN architectures. Deep belief networks, conditional RBMs and autoencoders are also discussed. Finally, two case studies are presented, concerning the use of deep NN architectures, one in the context of OCR and another in the context of autoencoding.