The simplicial neural cell and its mixed-signal circuit implementation: an efficient neural-network architecture for intelligent signal processing in portable multimedia applications

IEEE Transactions on Neural Networks - Tập 13 Số 4 - Trang 995-1008 - 2002
R. Dogaru1, P. Julian2,3, L.O. Chua4, M. Glesner5
1Department of Applied Electronics and Information Engineering, Polytechnic University of Bucharest, Bucharest, Romania
2Departamento de Ingineria Electrica, Universidad Nacional del Sur, Bahia Blanca, Argentina
3CONICET (Consejo Nacional Investigaciones Cientificasy Technicas), CONICET, Argentina
4Department of Electrical Engineering and Computer, University of California Berkeley, Berkeley, CA, USA
5Institute of Microelectronic Systems, Darmstadt University of Technology, Darmstadt, Germany

Tóm tắt

This paper introduces a novel neural architecture which is capable of similar performance to any of the "classic" neural paradigms while having a very simple and efficient mixed-signal implementation which makes it a valuable candidate for intelligent signal processing in portable multimedia applications. The architecture and its realization circuit are described and the functional capabilities of the novel neural architecture called a simplicial neural cell are demonstrated for both regression and classification problems including nonlinear image filtering.

Từ khóa

#Circuits #Very large scale integration #Signal processing #Filtering #Neural networks #Feedforward neural networks #Piecewise linear techniques #Application software #Support vector machines #Signal processing algorithms

Tài liệu tham khảo

lin, 1996, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems 10.1088/0957-4484/10/2/312 10.1109/ISCAS.2001.921258 10.1016/S0038-1101(99)00074-X castleman, 1996, Digital Image Processing hassoun, 1995, Fundamentals of Artificial Neural Networks 10.1109/81.847875 10.1109/ISCAS.2001.921355 10.1109/5.752516 10.1109/PGEC.1965.264137 10.1109/ICMNN.1994.593713 10.1073/pnas.61.4.1238 vapnik, 1998, Statistical Learning Theory 1995, Enhanced Learning for Evolutive Neural Architecture, Benchmark Data 10.1109/ICVD.1997.568194 10.1109/81.754847 10.1109/IJCNN.1999.831065 10.1109/81.728862 widrow, 1985, Adaptive Signal Processing dogaru, 2000, A compact universal cellular neural network cell based on resonant tunnelling diodes: Circuit design, model and functional capabilities, Proc Int Workshop Cellular Neural Networks Applicat, 183 10.1109/PROC.1977.10589 10.1109/TCS.1977.1084349 10.1142/S021812749900002X 10.1142/WSSNSA