Ad - a 256 625 ß ' Final

We describe two optical systems based on the radial basis function approach to pattern classification. An optical disk based system for handwritten character recognition is demonstrated. The optical system computes the Euclidean distance between an unknown input and 650 stored patterns at a demonstrated rate of 26,000 pattern comparisons per second. The ultimate performance of this system is limited by optical disk resolution to 10 binary operations per second. An adaptive system is also presented which facilitates on-line learning and provides additional robustness.