Extended Data Fig. 7: Linearity of feedback signals degrades with depth in deep convolutional network trained on ImageNet. | Nature Neuroscience

Extended Data Fig. 7: Linearity of feedback signals degrades with depth in deep convolutional network trained on ImageNet.

From: Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits

Extended Data Fig. 7: Linearity of feedback signals degrades with depth in deep convolutional network trained on ImageNet.

Each plot shows the change in burst probability of a unit in hidden layer l, Δpl, as the burst probability at the output layer, p8, is changed by Δp8 (n=1000), along with the Pearson’s correlation coefficient and two-tailed p-value (blue, top), as well as a random sample of 2000 burst probabilities after presentation of an input image (red, bottom).

Back to article page