Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification

Figure 6

Illustration of a simplified operational example of the convolutional layer and the average pooling layer over two time steps. At each time step, when the membrane potential exceeds the firing threshold of the neuron, the postneuron generates an output spike and resets. If no spike is generated, the membrane potential will leak over time. In the average pooling layer, the membrane potential will not leak over time.