Title :
Neural net with adaptive activation functions for face recognition
Author :
Talukder, Ashit ; Casasent, David
Author_Institution :
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
Abstract :
An efficient two-stage algorithm to compute nonlinear features is described. Its implementation on a neural net with adaptive activation functions that raise the input data to an arbitrary power is described. Its use in face recognition with unknown input poses is presented
Keywords :
covariance matrices; face recognition; feature extraction; neural nets; transfer functions; adaptive activation functions; nonlinear features; two-stage algorithm; unknown input poses; Closed-form solution; Covariance matrix; Erbium; Face recognition; Image reconstruction; Laboratories; Measurement standards; Neural networks; Power engineering computing; Propulsion;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861322
