AI Concepts and Foundations practice questions

Transfer learning

Why wrong: Transfer learning is a technique, not a problem description.

Underfitting

Why wrong: Underfitting would show poor performance even on training data.

Bias-variance tradeoff

Why wrong: This describes the balance but not the specific failure to generalize.

Apply L2 regularization

Why wrong: Regularization increases bias to reduce variance.

Increase the training dataset size

Why wrong: More data typically reduces variance, not bias.

Remove irrelevant features

Why wrong: Removing features simplifies the model, increasing bias.

Increase data augmentation

Why wrong: Augmentation helps but dropout is more targeted for overfitting.

Decrease the learning rate

Why wrong: Learning rate affects convergence, not generalization.

Increase the number of layers

Why wrong: More layers increase capacity, likely worsening overfitting.

Expert system

Why wrong: Expert systems rely on predefined rules, same limitation.

Natural language processing (NLP)

Why wrong: NLP is needed but the core improvement is ML.

Robotic process automation

Why wrong: RPA automates repetitive tasks, not conversational AI.

The model has no impact on fraud detection

Why wrong: It does detect some fraud, but misses many.

The model detects all fraudulent transactions

Why wrong: Low recall means many are missed.

Many legitimate transactions are flagged as fraud

Why wrong: That would be low precision, not low recall.

Collect more data

Why wrong: More data can help but is not the first step; regularization is quicker.

Use cross-validation

Why wrong: Cross-validation helps evaluate but does not fix overfitting.

Increase model complexity

Why wrong: This would likely worsen overfitting.

Unsupervised learning

Why wrong: Unsupervised learning finds patterns without labels, not classification.

Reinforcement learning

Why wrong: Reinforcement learning is for agent-based sequential decisions.

Regression

Why wrong: Regression predicts continuous values, not categories.

Feature scaling

Why wrong: Scaling does not address missing values.

One-hot encoding

Why wrong: Encoding is for categorical features, not missing values.

Principal component analysis (PCA)

Why wrong: PCA reduces dimensionality, not imputes missing data.

Cross-validation

Why wrong: Cross-validation is a method to evaluate models, not a cause of bias.

High regularization

Why wrong: Regularization reduces variance, not bias.

Supervised learning is only used for classification

Why wrong: Supervised learning includes regression as well.

Unsupervised learning always requires a target variable

Why wrong: Unsupervised learning has no target variable.

Supervised learning is a subset of reinforcement learning

Why wrong: They are distinct paradigms.

Vanishing gradients

Why wrong: Vanishing gradients would cause slow decrease in loss.

Underfitting

Why wrong: Underfitting would have high training loss as well.

Data leakage

Why wrong: Data leakage would cause abnormally high accuracy.

Training hyperparameters

Why wrong: Hyperparameters are already included.

Model type

Why wrong: Model type is already specified.

Evaluation metrics

Why wrong: Metrics can be defined separately; preprocessing is more fundamental.

Use a different dataset from a similar hospital without checking demographics

Why wrong: Using a different dataset without validation may perpetuate or introduce new biases.

Manually increase the weight of age-related features in the model

Why wrong: Manual weighting can introduce new biases and lacks systematic validation.

Replace the neural network with a decision tree to simplify decision logic

Why wrong: Model simplification does not guarantee fairness and may reduce performance.

Apply matrix factorization with higher latent factors

Why wrong: Matrix factorization still depends on interaction data and may not capture niche item features.

Increase the weight of popular items in the recommendation score

Why wrong: This would further bias toward popular items and worsen the long-tail problem.

Collect more user interaction data over time

Why wrong: More data won't help if niche items inherently have few interactions.

F1 score

Why wrong: F1 balances precision and recall, but recall alone is more appropriate when missing fraud is costly.

Precision

Why wrong: Precision focuses on false positives, not on catching fraud.

Accuracy

Why wrong: Accuracy is misleading on imbalanced datasets.

Reinforcement learning from human feedback

Why wrong: Reinforcement learning requires a reward signal and is not efficient for initial training.

Rule-based natural language processing

Why wrong: Rule-based systems require extensive manual rules and lack flexibility.

Convolutional neural networks (CNNs)

Why wrong: CNNs are designed for spatial data like images, not sequential text.

It predicts a target variable based on input features

Why wrong: Predicting a target variable is supervised learning.

It requires a reward signal to learn optimal actions

Why wrong: Reward signals are used in reinforcement learning.

It typically requires a separate validation set for tuning

Why wrong: Unsupervised learning often does not require a validation set.

All requests are allowed because the model is in the allowed list

Why wrong: The rate limit still applies and is exceeded.

All requests are denied because the rate limit is per minute and 150 exceeds the limit

Why wrong: The rate limit is per hour, not per minute.

All requests are denied because the second rule blocks all models

Why wrong: The second rule is a catch-all for unapproved models, but llama-3-70b is explicitly allowed.

Increase the defect classification threshold to reduce false positives

Why wrong: Does not address the root cause and may miss real defects.

Revert to the previous lighting setup by reinstalling bright, uniform lights

Why wrong: This is expensive and may not be possible in the new location.

Retrain the model from scratch using a large dataset of images from the new environment

Why wrong: Requires extensive labeling and downtime.

Remove the zip code feature from the model and retrain

Why wrong: Bias may persist through correlated features like income or credit history.

Increase the weight of samples from disadvantaged zip codes in the training data

Why wrong: Reweighting may not achieve strict fairness and can distort the model.

Retrain the model using only the unbiased validation set

Why wrong: The validation set is too small for training and may not represent the population.