Extended Data Fig. 3: Experimental distributions for different datasets.
From: Equivalent-accuracy accelerated neural-network training using analogue memory
(Extension of Fig. 5.) a–f, Weight probability density functions (PDFs) and cumulative distribution functions (CDFs) of device conductances for MNIST-backrand (a, b), CIFAR-10 transfer learning (c, d) and CIFAR-100 transfer learning (e, f). Results are shown for the initial condition and increasing epochs, from 1 to 20. For the CIFAR-100 experiment only, we increased the transfer interval to 16,000 images to reduce the overall wall-clock time.
