Which layer type is used to reduce the spatial dimensions in a CNN? a. Convolutional layer b. Pooling layer c. Fully connected layer d. Activation layer
Added by Rancho C.
Close
Step 1
Step 1: Understand the purpose of each layer type in a CNN. Show more…
Show all steps
Your feedback will help us improve your experience
Ivan Kochetkov and 55 other AP CS educators are ready to help you.
Ask a new question
Labs
Want to see this concept in action?
Explore this concept interactively to see how it behaves as you change inputs.
Key Concepts
Recommended Videos
Anand J.
Texts: Comprehension - A Three-Class Classification CNN Let's consider a CNN-based architecture designed to classify an image into one of three classes: a pedestrian, a tree, or a traffic signal. Each input image is of size (512, 512, 3) (RGB). The network contains the following 11 layers in order. Note that we will address the input layer as the first layer, the next convolution layer as the second layer, and so on (i.e., according to the numbers). 1. Input image (512, 512, 3) 2. Convolution: 32 5x5 filters, stride "s1", padding "p1" 3. Convolution: 32 3x3 filters, stride 1, padding 1 4. Max pooling: 2x2 filter, stride 2 5. Convolution: 64 3x3 filters, stride 1, padding 1 6. Convolution: 64 3x3 filters, stride 1, padding 1 7. Max pooling: 2x2 filter, stride 2 8. Layer 'l' 9. Fully connected: 4096 neurons 10. Fully connected: 512 neurons 11. Fully connected: 'F' neurons Comprehension: If the spatial dimensions (width and height) of the output going into the third layer are the same as the input from the previous layer, what could be the possible values of stride 's1' and padding 'p1'? A. stride 1, padding 1 (Incorrect option) B. stride 2, padding 2 C. stride 1, padding 2 D. stride 2, padding 1
Shu N.
Texts: More layers Suppose you make two CNN architectures, one with 15 layers (A) and another with 35 layers (B), and train them both (with identical infrastructure, training schemes, etc.) on a 10-class classification task. The performance of the models is as follows: Model A: Training accuracy = 85%; Validation accuracy = 82% Model B: Training accuracy = 78%; Validation accuracy = 73% Which of the following could be a possible explanation for these results? 1. As model B is huge, it is overfitting and, thus, not performing well. 2. As model B is huge, it is difficult to train (maybe because of infrastructural constraints or issues such as vanishing/exploding gradients). 3. Model B is underfitting, perhaps because larger networks sometimes have low "learning capacity."
Mauya M.
Recommended Textbooks
Computer Science and Information Technology
Introduction to Programming Using Python
Computer Science - An Overview
Transcript
Watch the video solution with this free unlock.
EMAIL
PASSWORD