Figure 2.

Test error of DNN with the MNIST dataset. Open white circles correspond to the baseline model with the training performed using the conventional update rule of Equation (1). (A) Lines marked as 1, 2, and 3 correspond to the stochastic model of Equation (2) with stochastic bit lengths BL = 1, 2, and 10, respectively. (B) Lines marked as 1, 2, and 3 correspond to the stochastic model with BL = 10 and the non-linearity ratio k = 0.5, 0.4, and 0.1, respectively. (C) Illustration of various non-linear responses of RPU device with k = 0, 0.5, and 1.