Robust low-sensitivity adaline neuron based on continuous valued number system

Analog Integrated Circuits and Signal Processing

Volumn 56, Issue 3, 2008, Pages 223-231

  Mirhassani, Mitra ^a   Ahmadi, Majid ^a   Jullien, Graham A ^b  

^a UNIVERSITY OF WINDSOR   (Canada)

^b UNIVERSITY OF CALGARY   (Canada)

Author keywords

Continuous Valued Number System (CVNS); CVNS Adaline neuron; Robust analog neural network

Indexed keywords

ARTIFICIAL INTELLIGENCE; DIGITAL ARITHMETIC; DIGITAL SIGNAL PROCESSING; FUNCTION EVALUATION; FUNCTIONS;

ADALINE; ANALOG CIRCUITRY; ANALOG NEURAL NETWORKS; CONTINUOUS VALUED NUMBER SYSTEM; CONTINUOUS VALUED NUMBER SYSTEM (CVNS); CVNS ADALINE NEURON; DIGIT LEVEL; INFORMATION REDUNDANCIES; LARGE SIZES; LOW SENSITIVITY; MODULAR ARITHMETIC; NON-LINEAR ACTIVATION FUNCTION; NUMBER SYSTEMS; ROBUST ANALOG NEURAL NETWORK; STOCHASTIC MODELLING;

NEURAL NETWORKS;

EID: 47149084750     PISSN: 09251030     EISSN: 15731979     Source Type: Journal    
DOI: 10.1007/s10470-008-9135-3     Document Type: Article

References (22)

1. Alippi, A., & Brizzo, L. (1998). Accuracy vs. precision in digital vlsi architectures for signal processing. IEEE Transaction on Neural Networks, 47(4), 472-477.
2. Andreou, A. G., Boahen, K. A., & Pouliquen, P. O. (1991). Current mode subthreshold MOS circuits for analog vlsi neural systems. IEEE Transactions on Neural Networks, 2(2), 205-213.
3. Arima, Y., Muraski, M., Yamada, T., Maeda, A., & Shinoharam, H. (1992). A refreshable analog VLSI neural network chip with 400 neurons and 40 k synapses. IEEE Journal of Solid State Circuits, 27(12), 1854-1861.
4. Basterretxea, K., Tarela, J. M., & del Campo, I. (2004). Approximation of sigmoid function and the derivative for hardware implementation of artificial neurons. IEE Proceedings on Circuits, Devices and Systems, 151(1), 8-24.
5. Bettola, S., & Piuri, V. (1997). High performance fault-tolerant digital neural networks. IEEE Transaction on Computers, 5(23), 230-233.
6. Cheng, A. Y., & Yeung, D. S. (1999). Sensitivity analysis of neocognitron. IEEE Transactions on Systems Man and Cybernetics, 29, 238-249.
7. Choi, J., & Sheu, B. J. (1993). A high precision VLSI winner take all circuit for self-organizing neural networks. IEEE Journal of Solid State Circuits, 28(2), 576-583.
8. Choi, J. Y., & Choi, C.-H. (1992). Sensitivity analysis of multilayer perceptron with differentiable activation functions. IEEE Transactions on Neural Networks, 3, 101-107.
9. Chow, M.-Y., & Tee, S. O. (1992). A measure of relative robustness for feed-forward neural networks subject to small input perturbations. International Journal of Neural Systems, 3(3), 291-299.
10. Djahanshahi, H., Ahmadi, M., Jullien, G. A., & Miller, W. C. (2001). Quantization noise improvement in a hybrid distributed-neuron ANN architecture. IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 48(9), 842-846.
11. Gowda, S. M., Sheu, B. J., & Choi, J. (1992) Design and characterization of analog neural network modules. IEEE Journal of Solid State Circuits, 28(3), 301-303.
12. He, Y., & Cilinhiroglu, U. (1993). A charge-based on-chip adaptation kohonen neural network. IEEE Transaction on Neural Networks, 4(3), 462-469.
13. Jabri, M., & Flower, B. (1992). Weight perturbation: An optimal architecture and learning technique for analog feed forward and recurrent multilayer networks. IEEE Transaction on Neural Networks, 3(1).
14. Lee, B. W., & Sheu, B. J. (1992). General purpose neural chips with electrically programmable synapses and gain adjustable neurons. IEEE Journal of Solid State Circuits, 27(9), 1299-1302.
15. Oh, S.-H., & Lee, Y. (1995). Sensitivity analysis of a single hidden-layer neural networks with threshold function. IEEE Transactions on Neural Networks, 6, 1005-1007.
16. Perfetti, R., & Ricci, E. (1998). Anoher k-winners-take-all analog neural network. IEEE Journal of Solid State Circuits, 11(4), 357-363.
17. Perfetti, R., & Ricci, E. (2000). Analog neural network for support vector machine learning. IEEE Journal of Solid State Circuits, 17(4), 829-836.
18. Piche, S. W. (1995). The selection of weight accuracies for Madaline. IEEE Transaction on Neural Network, 6(2), 432-445.
19. Widrow, B., & Hoff, M. E. (1960). Adaptive switching circuits. IRE WESCON Convetion Record, IRE Part 4, 96-104.
20. Yang, L., Hu, D., Luo, Y., & Zhang, X. (1997). Robustness analysis of feedforward neural networks composed of threshold neurons. Proceedings of the IEEE International Conference on Intelligent Processing Systems, 1, 502-506.
21. Zeng, X., & Yeung, D. S. (2001). Sensitivity analysis of multilayer perceptron to input and weight perturbation. IEEE Transaction on Neural Networks, 12(6), 1358-1366.
22. Zhang, D., & Elmasry, M. I. (2006). VLSI compressor design with applications to digital neural networks. IEEE Transaction on Very Large Scale Integration (VLSI) Systems, 47(3), 1085-1091.