Analysis of the Effects of Quantization in Multilayer Neural Networks Using a Statistical Model

IEEE Transactions on Neural Networks

Volumn 3, Issue 2, 1992, Pages 334-338

  Xie, Yun ^a   Jabri, Marwan A ^b  

^a TSINGHUA UNIVERSITY   (China)

^b UNIVERSITY OF SYDNEY   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

STATISTICAL METHODS;

EFFECTIVE NONLINEARITY COEFFICIENT; FEEDFORWARD NEURAL NETWORKS; MULTILAYER NEURAL NETWORKS; QUANTIZATION; STATISTICAL QUANTIZATION MODEL;

NEURAL NETWORKS;

EID: 0026836759     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.125876     Document Type: Article

References (4)

1. A. Krogh, J. Hertz, and R. G. Palmer, Introduction to the Theory of Neural Computation. Reading, MA: Addison Wesley, 1990.
2. M. A. Jabri and B. Flower, “Weight perturbation: An optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks,” in Neural Computation, MIT Press, to be published; also available as SEDAL Tech Report.
3. A. V. Oppenheim and R. W. Schafer, Digital Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1975, ch. 9.
4. Y. Xie, “Study on the training of multilayer neural networks with limited precision,” SEDAL Tech. Rep. 1991-8-3, Department of Electrical Engineering, University of Sydney, Aug. 1991.