We describe a hardware solution to a high-speed optical character recognition (OCR) problem. Noisy 15 × 10 binary images of machine written digits were processed and applied as input to Intel's Electrically Trainable Analog Neural Network (ETANN). In software simulation, we trained an 80 × 54 × 10 feedforward network using a modified version of backprop. We then downloaded the synaptic weights of the trained network to ETANN and tweaked them to account for differences between the simulation and the chip itself. The best recognition error rate was 0.9% in hardware with a 3.7% rejection rate on a 1000-character test set.