AI0-001 Machine Learning and Deep Learning Practice Test 3 — 15 Questions

Question 1

A deep learning engineer is training a convolutional neural network for image classification. The model is overfitting the training data. Which three techniques can help reduce overfitting? (Choose three.)

Accepted Answer

Add dropout layers. Dropout, data augmentation, and L2 regularization are standard techniques to reduce overfitting by adding regularization or increasing data diversity.

Answer

Use a smaller learning rate

Answer

Increase the number of convolutional layers

Question 2

A data scientist is evaluating a trained binary classification model. The model has high accuracy but the precision is low and recall is high. Which three actions are most appropriate to improve precision? (Choose three.)

Accepted Answer

Collect more training data for the minority class. Increasing the classification threshold reduces false positives, using a different algorithm that penalizes false positives more, and collecting more data for the minority class can all improve precision.

Answer

Apply oversampling to the majority class

Answer

Decrease the classification threshold

Question 3

Refer to the exhibit. A data scientist is training a neural network and observes the training log above. What is the most likely cause?

Accepted Answer

The learning rate is too high. The loss is increasing and accuracy decreasing, indicating divergence, which is typically caused by a learning rate that is too high.

Answer

The model is overfitting

Answer

The model is underfitting

Answer

The batch size is too large

Question 4

Refer to the exhibit. An AI specialist reviews the model evaluation report for a binary classifier. The specialist wants to improve recall. Which action is most likely effective?

Accepted Answer

Collect more training data for the minority class. Collecting more data for the minority class (the class with lower recall) helps the model learn better representations, often improving recall.

Answer

Decrease the classification threshold

Answer

Increase the classification threshold

Answer

Add more features

Question 5

Refer to the exhibit. An AI developer implements the above neural network architecture for handwritten digit recognition. The model achieves 85% training accuracy and 83% test accuracy. Which modification is most likely to improve training accuracy?

Accepted Answer

Remove the dropout layer. Removing the dropout layer reduces regularization, allowing the model to fit the training data better and increase training accuracy.

Answer

Increase the dropout rate to 0.7

Answer

Increase the number of filters in the first Conv2D layer

Answer

Add another dense layer before the output

Question 6

A data scientist is building a binary classification model to predict customer churn. The dataset has 10,000 samples with 80% non-churn and 20% churn. The model achieves 95% accuracy but fails to identify churners correctly. Which metric should the scientist focus on to evaluate model performance properly?

Accepted Answer

Recall (TPR). Option A is correct because recall (true positive rate) measures the ability to find positive (churn) cases, which is the goal in an imbalanced dataset. Option B, precision, is important but less critical when the cost of missing churners is high. Option C, F1-score, balances precision and recall but recall is more directly needed. Option D, specificity, measures true negative rate, not relevant for catching churners.

Answer

Precision

Answer

F1-score

Answer

Specificity

Question 7

A team is implementing a machine learning pipeline to classify images for a defect detection system. They are considering using a pre-trained convolutional neural network (CNN) and fine-tuning it on their small dataset. What is the primary advantage of transfer learning in this scenario?

Accepted Answer

It allows the model to leverage learned features from a large dataset, reducing training time and required data. Option C is correct because transfer learning leverages features learned from a large dataset, enabling effective training with a small dataset and reducing training time. Option A is incorrect because pre-trained models are often smaller, not larger. Option B is incorrect because preprocessing is still needed. Option D is incorrect because the model may retain biases from the original dataset.

Answer

It ensures the model is not biased toward the original dataset

Answer

It eliminates the need for data preprocessing

Answer

It reduces the risk of overfitting by using a larger model

Question 8

A company uses linear regression to predict sales based on advertising spend. The model's residuals show a pattern of increasing variance as spend increases. Which assumption of linear regression is violated?

Accepted Answer

Homoscedasticity. Option D is correct because homoscedasticity assumes constant variance of residuals; increasing variance indicates heteroscedasticity. Option A is incorrect because linearity is about the relationship, not residual variance. Option B is incorrect because independence refers to errors being independent. Option C is incorrect because normality is about the distribution of residuals, not variance.

Answer

Normality

Answer

Linearity

Answer

Independence

Question 9

An AI engineer is training a deep neural network for image recognition. The training loss decreases steadily for the first few epochs but then plateaus and starts to oscillate. Which adjustment is most likely to improve convergence?

Accepted Answer

Reduce the learning rate. Option B is correct because oscillating loss often indicates a learning rate that is too high; reducing it stabilizes training. Option A is incorrect because increasing the learning rate would worsen oscillation. Option C is incorrect because increasing batch size can help but not primarily address oscillation. Option D is incorrect because adding more layers could increase complexity and overfitting.

Answer

Add more layers

Answer

Increase the learning rate

Answer

Increase the batch size

Question 10

A healthcare organization wants to use patient data to predict disease risk. They are concerned about bias in the model. Which step is most critical during the data preparation phase to mitigate bias?

Accepted Answer

Ensuring the training data is representative of the target population. Option A is correct because ensuring the training data is representative of the target population is fundamental to avoid bias. Option B is incorrect because SMOTE addresses class imbalance, not bias from non-representative sampling. Option C is incorrect because model complexity does not directly address bias. Option D is incorrect because removing demographic features may not eliminate bias if proxy variables remain.

Answer

Applying SMOTE to oversample minority classes

Answer

Using a more complex algorithm

Answer

Removing all demographic features

Question 11

A team trains a random forest model on a dataset with 50 features. The model's performance on the test set is significantly worse than on the training set. Which technique is most appropriate to address this issue?

Accepted Answer

Apply cross-validation to tune hyperparameters and reduce overfitting. Option D is correct because cross-validation helps tune hyperparameters to reduce overfitting. Option A is incorrect because increasing trees reduces variance but may not be sufficient. Option B is incorrect because tree-based models are scale-invariant. Option C is incorrect because PCA can reduce dimensionality but may lose information; hyperparameter tuning is a better first step.

Answer

Increase the number of trees in the forest

Answer

Use feature scaling

Answer

Perform PCA to reduce dimensions

Question 12

A deep learning model for natural language processing uses a recurrent neural network (RNN) to process long sequences. The gradients vanish after many time steps. Which architectural change is most effective to mitigate this problem?

Accepted Answer

Replace the RNN cells with Long Short-Term Memory (LSTM) units. Option C is correct because LSTMs have gating mechanisms that allow gradients to flow longer, mitigating vanishing gradients. Option A is incorrect because more layers can exacerbate vanishing. Option B is incorrect because a larger learning rate may cause instability. Option D is incorrect because dropout addresses overfitting, not vanishing gradients.

Answer

Add dropout regularization

Answer

Use a larger learning rate

Answer

Increase the number of hidden layers

Question 13

An organization has a dataset with categorical features having high cardinality (e.g., ZIP codes). They plan to use a tree-based model. Which encoding method is most appropriate?

Accepted Answer

Target encoding (mean encoding). Option B is correct because target encoding replaces categories with the mean target value, capturing predictive power without explosion of features. Option A is incorrect because one-hot encoding creates many sparse features, inefficient for trees. Option C is incorrect because label encoding implies ordinality, which is misleading. Option D is incorrect because frequency encoding may lose target relationship.

Answer

Label encoding

Answer

One-hot encoding

Answer

Frequency encoding

Question 14

A company deploys a machine learning model that makes predictions on streaming data. Over time, the data distribution shifts, causing model performance to degrade. Which monitoring strategy is most appropriate to detect this drift?

Accepted Answer

Track the model's accuracy on a fixed validation set over time. Option A is correct because tracking accuracy on a fixed validation set over time directly reveals performance degradation due to distribution shift. Option B is incorrect because training loss may remain low even with drift. Option C is incorrect because retraining daily is a response, not a detection method. Option D is incorrect because comparing prediction distributions is less direct than performance metrics.

Answer

Compare the distribution of predictions to the training set

Answer

Monitor the model's training loss

Answer

Retrain the model daily on new data

Question 15

A data scientist is tuning hyperparameters for a support vector machine (SVM) with an RBF kernel. Which two hyperparameters most significantly affect model performance? (Select TWO.)

Accepted Answer

gamma (kernel coefficient). Options A and B are correct. C (regularization) controls the trade-off between margin and misclassification, and gamma defines the influence of a single training example. Option C is for polynomial kernel, not RBF. Option D is for regression SVM. Option E is not a hyperparameter for SVM.

Answer

learning rate

Answer

epsilon (for epsilon-SVR)

Answer

degree (for polynomial kernel)