Skip to main content
. 2018 Aug 23;12:524. doi: 10.3389/fnins.2018.00524

Figure 7.

Figure 7

(A) Classification accuracy of two-liquid SpiLinC, four-liquid SpiLinC, and Liquid-SNN vs. the total number of liquid neurons, evaluated on the MNIST testing dataset. (B) Reduction in the number of training examples offered by two-liquid SpiLinC and four-liquid SpiLinC over Liquid-SNN. (C) Sparsity in synaptic connectivity offered by two-liquid SpiLinC and four-liquid SpiLinC over Liquid-SNN.