Skip to main content
. 2017 Jun 21;11:324. doi: 10.3389/fnins.2017.00324

Figure 6.

Figure 6

(Left) MNIST Classification error using a fully connected 784-200-200-10 network with quantized synaptic weights and rounded using the randomized rounding (Muller and Indiveri, 2015). (Right) Histogram of synaptic weights of the quantized network after training.