Mixing floating- and fixed-point formats for neural network learning on neuroprocessors

We examine the efficient implementation of back-propagation (BP) type algorithms on TO [3], a vector processor with a fixed-point engine, designed for neural network simulation. Using Matrix Back Propagation (MBP) [2]we achieve an asymptotically optimal performance on TO (about 0.8 GOPS) for both forward and backward phases, which is not possible with the standard on-line BP algorithm. We use a mixture of fixed- and floating-point operations in order to guarantee both high efficiency and fast convergence. Though the most expensive computations are implemented in fixed-point, we achieve a rate of convergence that is comparable to the floating-point version. The time taken for conversion between fixed- and floating-point is also shown to be reasonably low.