GN6002 Machine Learning in Civil Engineering Quiz

Which type of neural network is commonly used for image recognition tasks in civil engineering?

• Recurrent Neural Networks (RNN)

• Convolutional Neural Networks (CNN)

• Multilayer Perceptrons (MLP)

• Deep Belief Networks (DBN)

In civil engineering applications, KNN can be used for:

• Predicting structural failure

• Analyzing traffic flow

• Soil classification

• All of the above

What is the primary advantage of using Convolutional Neural Networks (CNNs) in civil engineering applications?

• They require less computational resources.

• They can automatically learn features from raw data.

• They are less prone to overfitting.

• They are easier to train compared to other neural networks.

Which machine learning algorithm is commonly used for classification tasks and is based on the concept of finding the nearest data points to a given data point?

• Decision Trees

• K-Nearest Neighbors (KNN)

• Support Vector Machines (SVM)

• Linear Regression

In civil engineering, CNNs can be used for:

• Detecting cracks in infrastructure

• Predicting traffic congestion

• Analyzing satellite images for urban planning

• All of the above

Which of the following is NOT a typical layer found in a CNN?

• Convolutional layer

• Pooling layer

• Recurrent layer

• Fully connected layer

In CNNs, what is the purpose of the convolutional layer?

• To perform element-wise multiplication

• To detect patterns or features in the input data

• To apply activation functions

• To reduce the dimensionality of the data

What is the main objective of using machine learning in civil engineering?

• To design bridges

• To analyze traffic patterns

• To predict earthquakes

• All of the above

In K-Nearest Neighbors (KNN), what does the 'K' represent?

• Kernel

• K-value

• Number of nearest neighbors

• None of the above

Which of the following is NOT a step in the KNN algorithm?

• Calculate the distance between the query instance and all the training samples.

• Select the K nearest neighbors based on the calculated distances.

• Take the average of the K nearest neighbors to make a prediction.

• Adjust the weights of the nearest neighbors.