APPLICATION OF RECIRCULATION NEURAL NETWORK AND PRINCIPAL COMPONENT ANALYSIS FOR FACE RECOGNITION
Dmitry Bryliuk, В. В. Старовойтов · 2001
In this paper we describe our study of the recirculation neural network (RNN) for calculation principal components from a large set of face images. A new simple and fast algorithm was used to train RNN. Obtained principal components are used for face recognition. We also explore the ability of the RNN to reconstruct face images. Advantages of the proposed approach are shown.