AI0-001 AI Concepts and Foundations Practice Test 3 — 15 Questions

Question 1

A self-driving car company is developing an object detection system using a convolutional neural network (CNN). The system needs to detect pedestrians and vehicles in real-time with high accuracy. Which technique can reduce inference time while maintaining accuracy?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Apply model pruning and quantization. Model pruning removes redundant or less important weights from the CNN, reducing computational load, while quantization converts floating-point weights to lower-precision integers (e.g., INT8). Together, they shrink model size and speed up inference without significantly degrading accuracy, making them ideal for real-time object detection in resource-constrained environments like autonomous vehicles.

Answer

Use a pre-trained model and fine-tune it

Answer

Add more convolutional layers

Answer

Increase number of filters in each layer

Question 2

A marketing team wants to segment customers into groups based on purchasing behavior without predefined categories. Which algorithm should they use?

Accepted Answer

K-means clustering. K-means clustering is an unsupervised learning algorithm that groups data points into clusters based on similarity without requiring predefined labels. Since the marketing team wants to segment customers based on purchasing behavior without predefined categories, K-means is the correct choice as it discovers natural groupings in the data.

Answer

Naive Bayes classifier

Answer

Logistic regression

Answer

Support vector machine

Question 3

An AI model is being developed for medical diagnosis from X-ray images. The dataset contains only frontal chest X-rays. The model achieves high accuracy on test set but fails on lateral views. What is the most likely cause?

Accepted Answer

Dataset bias. The model was trained exclusively on frontal chest X-rays, so it never learned features specific to lateral views. When tested on lateral views, the distribution shift causes poor performance, which is a classic case of dataset bias (sampling bias). The high accuracy on the test set is misleading because the test set also only contained frontal views, masking the model's inability to generalize to other X-ray orientations.

Answer

Underfitting

Answer

Label noise

Answer

Overfitting

Question 4

A team is training a deep learning model for natural language processing using a large corpus. They notice the model has a very high number of parameters and training is slow. Which technique can reduce the number of parameters without significant performance loss?

Accepted Answer

Apply embedding compression. Embedding compression reduces the dimensionality of the embedding layer, which often contains the majority of the model's parameters in NLP tasks. By using techniques like low-rank factorization or pruning, the model retains most of its representational power while significantly decreasing the parameter count and training time.

Answer

Add more dropout layers

Answer

Use a larger batch size

Answer

Increase learning rate

Question 5

A data analyst needs to select two appropriate unsupervised learning techniques for clustering unlabeled data. (Choose two.)

Accepted Answer

Hierarchical clustering. Hierarchical clustering is an unsupervised learning technique that groups unlabeled data points into a tree-like structure (dendrogram) based on similarity, without requiring predefined cluster counts. It is appropriate for clustering tasks where the data lacks labels, making it a correct choice for this question.

Answer

Linear regression

Answer

Support vector machine

Answer

Decision tree

Question 6

When evaluating a binary classification model, which two metrics are most appropriate for imbalanced datasets? (Choose two.)

Accepted Answer

Recall. Recall (Option C) is correct because it measures the proportion of actual positive cases correctly identified, which is critical in imbalanced datasets where the minority class is of primary interest. Precision (Option E) is correct because it measures the accuracy of positive predictions, helping to avoid false positives when the positive class is rare. Together, recall and precision provide a balanced view of model performance on the minority class, unlike accuracy which can be misleadingly high by simply predicting the majority class.

Answer

Accuracy

Answer

Mean absolute error

Answer

R-squared

Question 7

Which three techniques are commonly used to mitigate overfitting in neural networks? (Choose three.)

Accepted Answer

Adding L2 regularization. Adding L2 regularization (also known as weight decay) penalizes large weights by adding a term proportional to the squared magnitude of the weights to the loss function. This forces the network to keep weights small, reducing the model's sensitivity to noise in the training data and preventing it from fitting spurious patterns, which is a direct and effective method to combat overfitting.

Answer

Increasing training data

Answer

Reducing number of layers

Question 8

Based on the exhibit, what is the most likely issue with the model training?

Accepted Answer

Overfitting. The exhibit shows training loss decreasing while validation loss increases after a certain point, which is a classic sign of overfitting. The model is memorizing the training data rather than generalizing, leading to poor performance on unseen validation data.

Answer

Vanishing gradient

Answer

Learning rate too high

Answer

Underfitting

Question 9

A data scientist notices the model overfits. Which change to the exhibit's configuration would most likely reduce overfitting?

Accepted Answer

Add L2 regularization to dense layers. Adding L2 regularization to dense layers penalizes large weights by adding a squared magnitude term to the loss function, which forces the model to learn simpler patterns and reduces overfitting. This directly addresses the core issue of the model memorizing noise in the training data.

Answer

Remove dropout layers

Answer

Increase learning rate to 0.01

Answer

Increase units in the first dense layer to 512

Question 10

Based on the exhibit, what issue should the team address?

Accepted Answer

Potential fairness bias across groups. The exhibit likely shows a confusion matrix or performance metrics broken down by demographic groups (e.g., race, gender), revealing that the model's false positive or false negative rates differ significantly across groups. This disparity indicates a potential fairness bias, which must be addressed to ensure equitable outcomes, especially in high-stakes AI applications like hiring or lending.

Answer

Model accuracy below threshold

Answer

High latency

Answer

Low throughput

Question 11

A data scientist is preparing a dataset for a classification task. The dataset contains 10,000 rows and 50 features, but many features have missing values. Which approach should the scientist take first to address the missing data?

Accepted Answer

Analyze the pattern and proportion of missing values to choose an appropriate imputation strategy.. The first step in handling missing data is to understand the pattern and proportion of missingness (e.g., MCAR, MAR, MNAR) to select an appropriate imputation method. Blindly applying imputation or deletion without analysis can introduce bias or reduce model performance. This diagnostic step ensures the chosen strategy aligns with the data's underlying structure and the classification task's requirements.

Answer

Use a deep learning model to predict missing values without preprocessing.

Answer

Remove all rows with any missing values to ensure a clean dataset.

Answer

Replace missing values with the mean of each feature immediately.

Question 12

A company built a speech-to-text model using a recurrent neural network (RNN). During deployment, the model performs poorly on accented speech. Which action would most effectively improve model robustness?

Accepted Answer

Augment the training dataset with various accented audio samples and retrain the model.. Augmenting the training dataset with diverse accented audio samples directly addresses the root cause of poor performance—distribution shift between training and deployment data. Retraining the model on this enriched dataset allows the RNN to learn invariant features across accents, improving generalization without altering the model architecture or risking catastrophic forgetting from fine-tuning on a tiny sample.

Answer

Collect a small sample of accented speech and fine-tune the model on that sample only.

Answer

Add dropout and reduce the number of RNN layers to prevent overfitting to the current data.

Answer

Replace the RNN with a convolutional neural network (CNN) for feature extraction.

Question 13

An AI team is deploying a predictive maintenance model for industrial equipment. The model predicts failure within a 30-day window. The cost of a false positive is 10% of the cost of a false negative. Which evaluation metric should the team prioritize?

Accepted Answer

F2 score (beta=2) to prioritize recall over precision.. The F2 score (beta=2) weights recall four times more than precision, which is appropriate because a false negative (missing a failure) costs 10 times more than a false positive (unnecessary maintenance). Prioritizing recall ensures the model captures as many true failures as possible, minimizing the higher-cost error type.

Answer

Area under the ROC curve (AUC-ROC) to measure overall discrimination.

Answer

F1 score to balance precision and recall equally.

Answer

Precision to minimize false positives.

Question 14

A marketing team uses a recommendation system to suggest products to customers. The system currently uses collaborative filtering. Which scenario would most likely cause the cold-start problem?

Accepted Answer

A new product is added to the catalog with no purchase history.. The cold-start problem occurs when a recommendation system lacks sufficient data to make accurate predictions. In collaborative filtering, recommendations rely on historical user-item interactions (e.g., purchase history). A new product with no purchase history has no interaction data, so the system cannot find similar users or items to generate recommendations, directly causing the cold-start problem.

Answer

The system switches from collaborative filtering to content-based filtering.

Answer

The website interface is redesigned, affecting user navigation.

Answer

A seasonal product experiences a sudden spike in sales.

Question 15

A hospital deploys an AI system to detect pneumonia from chest X-rays. The model achieves 95% accuracy on the test set but later is found to be less accurate for patients under 18. The development team suspects bias. Which step should be taken first to investigate?

Accepted Answer

Compute and compare performance metrics for different age subgroups in the test set.. The first step in investigating suspected model bias is to perform a disaggregated analysis of performance metrics across relevant subgroups, such as age brackets. This directly identifies whether the model's accuracy, precision, recall, or other metrics differ significantly for pediatric patients versus adults, confirming the presence and nature of the bias before any remediation is attempted.

Answer

Automatically retrain the model with a balanced dataset including more pediatric cases.

Answer

Expand the test set with more pediatric X-rays and re-evaluate overall accuracy.

Answer

Add more features to the model to capture age-related anatomical differences.