003-3-IMG

Which code snippet correctly compiles a CNN model for classifying handwritten digits with appropriate loss function and optimizer in TensorFlow/Keras?

• model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

• model.compile(loss='mean_squared_error', optimizer='sgd', metrics=['accuracy'])

• model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

• model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['loss'])

In an AI project, you are building a Convolutional Neural Network (CNN) for image classification. You have a dataset of animal images with three classes: 'cat', 'dog', and 'rabbit'. Which of the following code snippets correctly defines the output layer of the CNN model using TensorFlow/Keras for this classification task?

• model.add(Dense(3, activation='softmax'))

• model.add(Dense(1, activation='sigmoid'))

• model.add(Dense(3, activation='sigmoid'))

• model.add(Dense(3, activation='relu'))

Which of the following sequences represents the typical steps involved in a Convolutional Neural Network (CNN) classification project?

• Data preprocessing, model training, model evaluation, data augmentation.

• Model evaluation, data preprocessing, data augmentation, model training.

• Data preprocessing, data augmentation, model training, model evaluation.

• Model training, data preprocessing, model evaluation, data augmentation.

Which of the following preprocessing steps is typically performed on the dataset before training a Convolutional Neural Network (CNN) for image classification?

• Normalizing pixel values to the range [0, 1] or [-1, 1].

• Resizing images to a fixed size.

• Applying data augmentation techniques.

• All of the above.

Which of the following statements best describes data augmentation in the context of training a Convolutional Neural Network (CNN)?

• Data augmentation involves reducing the size of the training dataset to improve computational efficiency.

• Data augmentation refers to increasing the diversity of the training dataset by adding noisy samples.

• Data augmentation involves applying transformations to the existing training data to create new, slightly modified samples.

• Data augmentation is the process of selecting a subset of features that are most relevant to the task.

Which of the following techniques is commonly used to avoid overfitting when training a machine learning model?

• Increasing the complexity of the model.

• Using a smaller training dataset.

• Applying regularization techniques.

• Avoiding data augmentation.

• 
• 
• 
• 

Which of the following code snippets correctly converts a list to a NumPy array?

• 
• 
• 
• 

Which of the following code snippets correctly normalizes the X_values array by dividing each element by 255?

• 
• 
• 
• 

Suppose you have a dataset X_values containing image data stored as a NumPy array with shape (num_samples, height, width, channels), where num_samples is the number of images, height and width are the dimensions of each image, and channels represents the number of color channels (e.g., 3 for RGB images). Which of the following code snippets correctly reshapes X_values to fit into the shape required for training a CNN?

• 
• 
• 
•