You are reading immutable version 3. The current guide may be newer.

Study the paper

Deep Residual Learning for Image Recognition

Lessons, visuals, quizzes, flashcards, and resources—organized in teaching order.

All activities

Empirical Analysis and Layer Responses

Standard deviations of layer responses on CIFAR-10

Standard deviations of layer responses on CIFAR-10

The standard deviations (std) of layer responses on CIFAR-10 are analyzed to understand the behavior of residual learning. The responses are measured at the outputs of each 3×33\times3 layer, after Batch Normalization (BN) and before nonlinearity.

Sources

S4.F7

Figure 7: Standard deviations (std) of layer responses on CIFAR-10. The responses are the outputs of each 3×\times3 layer, after BN and before nonlinearity. Top: the layers are shown in their original order. Bottom: the responses are ranked in descending order.

Figure 7 shows the standard deviations of layer responses on CIFAR-10. In the top plot, the layers are shown in their original order. In the bottom plot, the responses are ranked in descending order.

Sources

S4.F7

Figure 7: Standard deviations (std) of layer responses on CIFAR-10. The responses are the outputs of each 3×\times3 layer, after BN and before nonlinearity. Top: the layers are shown in their original order. Bottom: the responses are ranked in descending order.
Reported values
MeasureValue
Sources

S4.F7

Figure 7: Standard deviations (std) of layer responses on CIFAR-10. The responses are the outputs of each 3×\times3 layer, after BN and before nonlinearity. Top: the layers are shown in their original order. Bottom: the responses are ranked in descending order.