Figure 3 shows a ResNet block where the input all is a two-dimensional vector: [0.5, -...

 

Transcribed Image Text:

Figure 3 shows a ResNet block where the input all is a two-dimensional vector: [0.5, - 0.5]. The two layers inside the ResNet block consist of two dense layers, each having two nodes. The weight values for the first layer are [-0.3, 0.7] and [0.5, -0.4], respectively. The weight values for the second layer are [0.7, -0.3] and [-0.5, -0.3], respectively. Ignore bias and use ReLu() as the activation functions for all nodes. • • Calculate output of the first layer of the ResNet block, i.e., all+¹) (show calculations) [0.5 pt] Calculate output of the second layer of the ResNet block, i.e., all+2) (show calculations) [0.5 pt] If the skip connection of the ResNet block does not exist, what is the output of the block, i.e., all+21 (show calculations) [0.5 pt] Explain motivation of ResNet block (i.e., what is the learning objective of the ResNet block) [0.5 pt] all all+1] Figure 3 all+2] Figure 3 shows a ResNet block where the input all is a two-dimensional vector: [0.5, - 0.5]. The two layers inside the ResNet block consist of two dense layers, each having two nodes. The weight values for the first layer are [-0.3, 0.7] and [0.5, -0.4], respectively. The weight values for the second layer are [0.7, -0.3] and [-0.5, -0.3], respectively. Ignore bias and use ReLu() as the activation functions for all nodes. • • Calculate output of the first layer of the ResNet block, i.e., all+¹) (show calculations) [0.5 pt] Calculate output of the second layer of the ResNet block, i.e., all+2) (show calculations) [0.5 pt] If the skip connection of the ResNet block does not exist, what is the output of the block, i.e., all+21 (show calculations) [0.5 pt] Explain motivation of ResNet block (i.e., what is the learning objective of the ResNet block) [0.5 pt] all all+1] Figure 3 all+2]