Adaptive spline neural networks for signal processing applications
作者： Francesco Piazza , Aurelio Uneini
DOI:
关键词: Artificial neural network 、 Artificial intelligence 、 Signal processing 、 Spline (mathematics) 、 Nonlinear system 、 Computer science 、 Digital signal processing
摘要: In this paper, we study the properties of a new kind real and complex domain artificial neural networks called adaptive spline (ASNN), which are able to adapt their activation functions by varying control points Catmull-Rom cubic spline. Most all, interested in generalization capability can show that architecture be seen as sub-optimal realization additive based model obtained reguralization theory. This network implemented very simple structure being improve capabilities using few training epochs. Due its low architectural complexity used cope with several nonlinear DSP problem at high throughput rate.
uncini.com 参考文章(16)
N. Benvenuto, M. Marchesi, F. Piazza, A. Uncini, A COMPARISON BETWEEN REAL AND COMPLEX VALUED NEURAL NETWORKS IN COMMUNICATION APPLICATIONS international conference on artificial neural networks. pp. 1177- 1180 ,(1991) , 10.1016/B978-0-444-89178-5.50046-4
Edwin Catmull, Raphael Rom, A CLASS OF LOCAL INTERPOLATING SPLINES Computer Aided Geometric Design. pp. 317- 326 ,(1974) , 10.1016/B978-0-12-079050-0.50020-5
S Haykin, Adaptive Filter Theory ,(1986)
N. Benvenuto, M. Marchesi, F. Piazza, A. Uncini, Non linear satellite radio links equalized using blind neural networks international conference on acoustics, speech, and signal processing. pp. 1521- 1524 ,(1991) , 10.1109/ICASSP.1991.150526
Chyi-Tsong Chen, Wei-Der Chang, A feedforward neural network with function shape autotuning Neural Networks. ,vol. 9, pp. 627- 641 ,(1996) , 10.1016/0893-6080(96)00006-8
N. Benvenuto, F. Piazza, On the complex backpropagation algorithm IEEE Transactions on Signal Processing. ,vol. 40, pp. 967- 969 ,(1992) , 10.1109/78.127967
H. Leung, S. Haykin, The complex backpropagation algorithm IEEE Transactions on Signal Processing. ,vol. 39, pp. 2101- 2104 ,(1991) , 10.1109/78.134446
P. Campolucci, F. Capperelli, S. Guarnieri, F. Piazza, A. Uncini, Neural networks with adaptive spline activation function Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96). ,vol. 3, pp. 1442- 1445 ,(1996) , 10.1109/MELCON.1996.551220
A.A.M. Saleh, Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifiers IEEE Transactions on Communications. ,vol. 29, pp. 1715- 1720 ,(1981) , 10.1109/TCOM.1981.1094911
B. Widrow, M.A. Lehr, 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation Proceedings of the IEEE. ,vol. 78, pp. 1415- 1442 ,(1990) , 10.1109/5.58323