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

Figure 3.

Figure 3

Illustration of the Spiking Liquid-Ensemble Computing (SpiLinC) architecture composed of a distributed arrangement of multiple liquids operating in parallel. (A) Two-liquid SpiLinC, where each liquid constituting the ensemble is trained with different frequency channels of a speech signal (utterance of “0” in this example). (B) Four-liquid SpiLinC, where the individual liquids are trained with separate partitions of an image pattern.