Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103410Q (2017) https://doi.org/10.1117/12.2268722
This paper explores method of layer-by-layer training for neural networks to train neural network, that use approximate calculations and/or low precision data types. Proposed method allows to improve recognition accuracy using standard training algorithms and tools. At the same time, it allows to speed up neural network calculations using fast-processed approximate calculations and compact data types. We consider 8-bit fixed-point arithmetic as the example of such approximation for image recognition problems. In the end, we show significant accuracy increase for considered approximation along with processing speedup.