论文信息 - Adaptive, optical, radial basis function neural network for handwritten digit recognition.

Adaptive, optical, radial basis function neural network for handwritten digit recognition.

An adaptive, optical, radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially multiplexed system that incorporates an on-line adaptation of weights and basis function widths to provide robustness to optical system imperfections and system noise. The optical system computes the Euclidean distances between a 100-dimensional input vector and 198 stored reference patterns in parallel by using dual vector-matrix multipliers and a contrastreversing spatial light modulator. Software is used to emulate an electronic chip that performs the on-line learning of the weights and basis function widths. An experimental recognition rate of 92.7% correct out of 300 testing samples is achieved with the adaptive training, versus 31.0% correct for nonadaptive training. We compare the experimental results with a detailed computer model of the system in order to analyze the influence of various noise sources on the system performance.

W E Foor | M A Neifeld | M. Neifeld | W. E. Foor

[1] D Psaltis,et al. Optical implementation of the Hopfield model. , 1985, Applied optics.

[2] Ibrahim Abdulhalim,et al. High‐speed analog spatial light modulator using a hydrogenated amorphous silicon photosensor and an electroclinic liquid crystal , 1989 .

[3] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.

[4] Yuchun Lee,et al. Handwritten Digit Recognition Using K Nearest-Neighbor, Radial-Basis Function, and Backpropagation Neural Networks , 1991, Neural Computation.

[5] K M Johnson,et al. Noise analysis of polarization-based optoelectronic connectionist machines. , 1992, Applied optics.

[6] Mohamad T. Musavi,et al. On the training of radial basis function classifiers , 1992, Neural Networks.

[7] Mark A. Handschy,et al. High-speed binary optically addressed spatial light modulator , 1989 .

[8] M A Neifeld,et al. Optical implementations of radial basis classifiers. , 1993, Applied optics.

[9] D P Casasent,et al. Error-source effects in a high-accuracy optical finite-element processor. , 1986, Applied optics.

[10] D. Brady,et al. Adaptive optical networks using photorefractive crystals. , 1988, Applied optics.

[11] T. Poggio,et al. A network that learns to recognize three-dimensional objects , 1990, Nature.