Eduard Säckinger, Bernhard Boser, Lawrence Jackel
A board is described that contains the ANN A neural-network chip, and a DSP32C digital signal processor. The ANNA (Analog Neural Network Arithmetic unit) chip performs mixed analog/digital processing. The combination of ANNA with the DSP allows high-speed, end-to-end ex(cid:173) ecution of numerous signal-processing applications, including the prepro(cid:173) cessing, the neural-net calculations, and the postprocessing steps. The ANNA board evaluates neural networks 10 to 100 times faster than the DSP alone. The board is suitable for implementing large (million con(cid:173) nections) networks with sparse weight matrices. Three applications have been implemented on the board: a convolver network for slant detection of text blocks, a handwritten digit recognizer, and a neural network for recognition-based segmentation.