Exercises

These exercises check the convolution ideas from the chapter.

DL-C14-C-001Exercise: Patch size

A local patch is 5 x 5. How many positions does it contain?

Compute it first, then check your number.

DL-C14-C-002Exercise: Convolution output

Input window [3, 1, 2] uses kernel [2, 0, -1]. What is the output?

Compute it first, then check your number.

DL-C14-C-003Exercise: Feature maps

A convolutional layer has 20 kernels. How many feature maps does it produce?

Compute it first, then check your number.

DL-C14-C-004Exercise: Valid output length

For input length 10, kernel size 4, and stride 2, what is floor((10 - 4) / 2) + 1?

Compute it first, then check your number.

DL-C14-C-005Exercise: Kernel weights

A kernel is 5 x 5 and reads 3 input channels. How many weights does it have?

Compute it first, then check your number.

DL-C14-C-006Exercise: Max pooling

What is the max of [7, 2, 5, 9]?

Compute it first, then check your number.

DL-C14-C-007Exercise: Parameter sharing

Enter 1 if convolution reuses the same kernel across positions, or 2 if it always learns a separate kernel for every position.

Compute it first, then check your number.