Question23 Which of the following statements is/are CORRECT about a convolutional layer? (you can chose more than one) The number of weights depends on the depth of the input volume The total number of parameters depends on the padding The total number of parameters depends on the stride The number of biases is equal to the number of filters ResetMaximum marks: 1.5 Flag question undefined

Question

BlackTom AI · Accepted Answer

First, let’s restate the question in our own words to set the stage: we’re evaluating which statements about a convolutional layer are correct, with multiple options possible.
Option 1: 'The number of weights depends on the depth of the input volume.' In a typical 2D convolution, each filter has a weight tensor whose size is (kernel_height x kernel_width x input_depth). Therefore, as the input depth (number of channels) increases, the total number of weights for each filter increases proportionally. This makes the statement true.
Option 2: 'The total number of parameters depends on the padding.' Padding affects the spatial dimensions of the output feature map, not the learnable parameters themselves. The kernel weights and biases are fixed given the filter size and the number of filters, regardless of padding. Hence, this statement is false.
Option 3: 'The total number of parameters depends on the stride.' Similar to padding, stride changes how the output size is computed but does not alter the number of weights or biases per layer. The parameter count remains determined by the filter dimensions and the number of filters. Thus, this statement is false.
Option 4: 'The number of biases is equal to the number of filters.' In standard convolutional layers, there is one bias per filter, so the total number of biases equals the number of filters. This statement is true.
In summary, the correctness hinges on understanding what determines parameter counts: the depth and kernel size govern the weights per filter, and the number of filters determines biases; padding and stride influence output dimensions but not the total count of learnable parameters. The first and fourth statements align with this understanding, while the second and third do not. These distinctions help prevent common misconceptions about how architectural choices impact parameter counts.

View Explanation

Log in for full answers

Similar Questions

Which of the following Neural Networks is used in Machine Vision system?

哪一项陈述正确描述了卷积神经网络 (CNN) 在识别中的特征？ Which statement describes a characteristic of the Convolutional Neural Network (CNN) in recognition correctly?

This is the CNN Architecture diagram that was explained in lectures. Match A, B, C, D, and E to the correct labels below. Note: Full marks will only be awarded for getting all matches correct here. You must make selections in all drop down lists in order for this question to be counted.

In implementing CNNs, we actually implement the forwards pass as a cross-correlation. This means that for the backward pass, the gradient of the loss with respect to the input is

Convolutional layers are

Max pooling layers are:

What is the most typical use for a convolutional neural network?

More Practical Tools for Students Powered by AI Study Helper

Homework AI Solver

Stylized AI Paper Writer

Plagiarism Checker Assistant

Citation AI Academic Writing Tool

In-Class Translation Assistant

AI Note Generator

AI Quiz Answers

Past Exam Questions from University Test Bank

Smart Practice Assistant

Adaptive Practice

Making Your Study Simpler