A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision

Abstract

Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple and efficient. The proposed method succeeds in training NNs with 16-bit fixed-point numbers and provides faster convergence and higher classification accuracy than both CSR and deterministic rounding-to-the-nearest method.

References in corpus (1)

• Training Deep Neural Networks with 8-bit Floating Point Numbers