Questions for the machine learning homework.

Question 4: Assuming the following FC layer in a NN with two filters of size 3x3x3, and input fmap. Channel 3 0.1 -0.5 0.2 0.2 -0.5, 0.2 0.1 -0.2 0.3 |2 1 4, | 2 3 5 Channel 3 4 1 2 Channel 2 0.2 -0.6 0.1 0.5 0.2 0.1 0.2 -0.4 0.1 3 5 A 16 2,2 Channel 2 Channel 1 0.1 0.4 0.2 Channel 1 0.2 -0.1 0.1 0.3 -0.2 0.1 Filter 1 2 1 5 4 2 1 1 4 3 Input fmap 0.4 -0.2 0,4 Channel 3 0.3 -0.2 0.2 0.2 -0.1 0.3 0.4 -0.1 0.2 Channel 2 |0.1 0.3 6.4 0.4 -0.2 0.5 0.2 -0.3 0.1 Channel 1 0.1 -0.1 0.2 0.3 0.2 0.3 Filter 2 a) Demonstrate the corresponding FC layer in the form of Matrix Multiplication and calculate the output fmap. Please keep in mind that you may need to flatten the filters and input fmaps. You can assume RELU as an activation function. [20 points] Question 4: Assuming the following FC layer in a NN with two filters of size 3x3x3, and input fmap. Channel 3 0.1 -0.5 0.2 0.2 -0.5, 0.2 0.1 -0.2 0.3 |2 1 4, | 2 3 5 Channel 3 4 1 2 Channel 2 0.2 -0.6 0.1 0.5 0.2 0.1 0.2 -0.4 0.1 3 5 A 16 2,2 Channel 2 Channel 1 0.1 0.4 0.2 Channel 1 0.2 -0.1 0.1 0.3 -0.2 0.1 Filter 1 2 1 5 4 2 1 1 4 3 Input fmap 0.4 -0.2 0,4 Channel 3 0.3 -0.2 0.2 0.2 -0.1 0.3 0.4 -0.1 0.2 Channel 2 |0.1 0.3 6.4 0.4 -0.2 0.5 0.2 -0.3 0.1 Channel 1 0.1 -0.1 0.2 0.3 0.2 0.3 Filter 2 a) Demonstrate the corresponding FC layer in the form of Matrix Multiplication and calculate the output fmap. Please keep in mind that you may need to flatten the filters and input fmaps. You can assume RELU as an activation function. [20 points]