Behavior of the simulated spiking network for the MNIST dataset.

a: Behavior of the network during a typical image presentation; compare with Fig 1b. Time period of external stimulation shown by grey bar. Raster plot includes all neurons which fired at least one spike during the presentation. The spikes of the visible neurons are in the bottom row and those of the hidden neurons are directly above. The top two rows, in grey, show the spikes for the inhibitory pools at each layer. Although the each training presentation ran for 65ms, all spikes occurred before 30ms so the raster plot was ended there. b: Reconstruction loss function, black dots, (defined in text) decreases over time, as does sparsity loss function (red, note log scale on y axis). c: The trained networks’ attempted reconstruction of representative training images. Each image shows the ON cell values minus the OFF cells. The first row shows the inputs to the network. The second row shows the attempted reconstruction .

a: 典型图像呈现过程中神经网络的行为表现，可与图1b对照。灰色条标注了外部刺激的施加时段。脉冲序列图（raster plot）涵盖了本次图像呈现期间至少触发一次动作电位的所有神经元。可见神经元的动作电位分布于最下方一行，隐藏神经元的动作电位紧随其上。顶部两行灰色区域分别展示了各层抑制性神经元池的动作电位。尽管单次训练图像呈现时长为65ms，但所有动作电位均在30ms前产生，因此脉冲序列图仅截取至该时刻。
b: 重构损失函数（文中已定义，以黑色圆点标记）随时间推移逐渐降低，稀疏性损失函数（以红色圆点标记，请注意纵轴采用对数刻度）亦呈下降趋势。
c: 经训练的网络对代表性训练图像的重构结果。每幅图均展示了ON细胞（ON cell）与OFF细胞（OFF cell）的数值差值。第一行展示了网络的输入图像，第二行则为网络尝试完成的重构结果。