Why CNNs detect spatial patterns in PyTorch - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why do CNNs use filters?

Why do convolutional neural networks (CNNs) use filters (also called kernels) when processing images?

A Filters scan the image to detect local patterns like edges or textures by focusing on small regions.

B Filters randomly change pixel values to increase image diversity.

C Filters convert images into text descriptions for easier processing.

D Filters remove all colors to simplify the image into black and white.

💡 Hint

Think about how looking at small parts of a picture helps you recognize shapes.

CNN filters slide over small parts of an image to find simple patterns like edges or textures. These patterns help the network understand the image step by step.

❓ Predict Output

intermediate

Output shape after convolution

Given a grayscale image tensor of shape (1, 1, 28, 28) and a convolution layer with 6 filters of size 3x3, stride 1, and padding 0, what is the output shape after applying the convolution?

PyTorch

import torch
import torch.nn as nn

image = torch.randn(1, 1, 28, 28)  # batch=1, channels=1, height=28, width=28
conv = nn.Conv2d(in_channels=1, out_channels=6, kernel_size=3, stride=1, padding=0)
output = conv(image)
print(output.shape)

A torch.Size([1, 6, 26, 26])

B torch.Size([1, 6, 28, 28])

C torch.Size([1, 1, 26, 26])

D torch.Size([6, 1, 28, 28])

💡 Hint

Output size = (Input size - Kernel size + 2 * Padding) / Stride + 1

With input 28x28, kernel 3x3, stride 1, padding 0, output height and width = 28 - 3 + 0 + 1 = 26. Number of output channels = 6 filters.

❓ Model Choice

advanced

Choosing CNN for spatial pattern detection

You want to build a model to recognize handwritten digits from images. Which model type is best suited to detect spatial patterns like edges and curves?

A A linear regression model that predicts digits directly from pixel values.

B A simple feedforward neural network with fully connected layers only.

C A convolutional neural network (CNN) because it captures local spatial features using filters.

D A recurrent neural network (RNN) designed for sequential data like text.

💡 Hint

Think about which model type is designed to understand images by looking at small parts.

CNNs are designed to detect spatial patterns by applying filters over image regions, making them ideal for image tasks like digit recognition.

❓ Hyperparameter

advanced

Effect of kernel size on spatial pattern detection

How does increasing the kernel size in a CNN layer affect the spatial patterns the model can detect?

A Larger kernels always improve model accuracy without any drawbacks.

B Larger kernels capture bigger spatial patterns but reduce the output size more.

C Larger kernels ignore spatial patterns and treat the image as a flat vector.

D Larger kernels decrease the number of filters in the layer automatically.

💡 Hint

Think about how a bigger window sees more of the image at once.

Larger kernels look at bigger areas of the image, detecting larger patterns but also reducing the output feature map size more due to less sliding positions.

❓ Metrics

expert

Interpreting CNN training loss and accuracy

During CNN training on image data, you observe the training loss steadily decreases but the validation accuracy stops improving and fluctuates. What does this indicate?

A The training data is corrupted and causing unstable validation results.

B The model is underfitting and needs more training epochs.

C The model has perfect generalization and no further tuning is needed.

D The model is overfitting the training data and not generalizing well to new data.

💡 Hint

Think about what it means when training improves but validation does not.

When training loss decreases but validation accuracy fluctuates or stops improving, the model is likely memorizing training data patterns and failing to generalize, which is overfitting.