AI0-001 AI Concepts and Techniques Practice Test 2 — 15 Questions

Question 1

A company wants to build a customer service chatbot that answers questions about their internal policy documents. The documents are updated monthly, and the team cannot afford to retrain a model each time. Which approach is MOST appropriate?

Accepted Answer

Use Retrieval-Augmented Generation (RAG) with the policy documents indexed in a vector store. Retrieval-Augmented Generation (RAG) is the most appropriate approach because it allows the chatbot to answer questions based on the latest policy documents without retraining the model. By indexing the documents in a vector store and retrieving relevant chunks at query time, RAG provides up-to-date, contextually accurate answers while keeping the underlying LLM static, which avoids the cost and complexity of monthly retraining.

Answer

Use a larger foundation model with a longer context window and paste all documents into each prompt

Answer

Fine-tune a base LLM on the policy documents monthly

Answer

Train a custom model from scratch on the policy documents each month

Question 2

A data scientist is building a model to predict whether a credit card transaction is fraudulent, using labeled historical data. Which machine learning paradigm is being used?

Accepted Answer

Supervised learning. Supervised learning uses labeled data to train a model to map inputs to outputs. Fraud detection with historical labels is a classic binary classification problem.

Answer

Reinforcement learning

Answer

Unsupervised learning

Answer

Self-supervised learning

Question 3

A deep learning engineer is training a transformer model and notices that validation perplexity increases after a few epochs while training perplexity continues to decrease. Which of the following is the MOST likely cause?

Accepted Answer

The model is overfitting the training data. Option D is correct because the described pattern—decreasing training perplexity alongside increasing validation perplexity—is the classic signature of overfitting. The model is memorizing the training data rather than learning generalizable patterns, causing its performance on unseen validation data to degrade after a certain point in training.

Answer

The temperature parameter is set too high

Answer

The batch size is too small

Answer

The learning rate is too low

Question 4

A product team wants a system that can generate high-quality synthetic images of furniture in different room settings for an online catalog. The images must be photorealistic and vary in style. Which generative AI approach is BEST suited for this task?

Accepted Answer

Diffusion model. Diffusion models are the best choice because they iteratively denoise random noise to produce high-quality, photorealistic images with diverse styles. Unlike GANs, they avoid mode collapse and training instability, and they generate more detailed and varied outputs than VAEs, making them ideal for furniture catalog images in different room settings.

Answer

Variational autoencoder (VAE)

Answer

Generative adversarial network (GAN)

Answer

Recurrent neural network (RNN)

Question 5

An AI practitioner needs to measure the performance of a binary classification model for disease detection, where the cost of false negatives is very high. Which metric should be prioritized?

Accepted Answer

Recall. Recall (true positive rate) minimises false negatives, which is critical when missing a positive case is dangerous.

Answer

Precision

Answer

F1-score

Answer

Accuracy

Question 6

A data scientist is using a linear regression model to predict house prices and observes that the model performs well on training data but poorly on test data. Which regularisation technique is MOST appropriate to reduce overfitting?

Accepted Answer

L2 regularisation (Ridge). L2 regularisation (Ridge) adds a penalty term equal to the sum of the squared coefficients to the loss function, which shrinks coefficient magnitudes without forcing them to zero. This reduces variance and overfitting by making the model less sensitive to individual features, which is ideal when the model performs well on training data but poorly on test data due to high variance.

Answer

L1 regularisation (Lasso)

Answer

Dropout

Answer

Data augmentation

Question 7

A team is developing a sentiment analysis model and obtains the following performance on the test set: accuracy=0.92, precision=0.75, recall=0.80, F1=0.77. The baseline majority-class classifier achieves 0.85 accuracy. Which conclusion is MOST justified?

Accepted Answer

The model likely suffers from class imbalance, as the gap between accuracy and precision suggests. Accuracy is high but precision and recall are notably lower, indicating class imbalance where the model biases toward the majority class, inflating accuracy.

Answer

The model should use a different evaluation metric like BLEU

Answer

The model is excellent because accuracy is high

Answer

The model has high variance and is overfitting

Question 8

An AI engineer is designing a system to detect unusual patterns in network traffic that may indicate a security breach. The system should learn from normal traffic patterns and flag deviations. Which machine learning approach is MOST appropriate?

Accepted Answer

Unsupervised anomaly detection. Unsupervised anomaly detection is the most appropriate approach because the system must learn 'normal' traffic patterns from unlabeled data and then flag deviations without requiring pre-labeled examples of attacks. This aligns with the core requirement of detecting unknown or novel security breaches, which supervised methods cannot handle due to the lack of labeled attack data.

Answer

Reinforcement learning with reward shaping

Answer

Supervised classification using logistic regression

Answer

Semi-supervised learning with a small labeled set

Question 9

A machine learning engineer is training a neural network for image classification. The training loss decreases slowly and the model accuracy improves only marginally each epoch. Which hyperparameter adjustment is MOST likely to accelerate convergence?

Accepted Answer

Increase the learning rate. The training loss decreasing slowly and accuracy improving marginally each epoch indicates that the learning rate is too small, causing the optimizer to take very small steps toward the minimum of the loss function. Increasing the learning rate allows the optimizer to take larger steps per update, which accelerates convergence. Option C is correct because adjusting the learning rate directly addresses the step size in gradient descent.

Answer

Add more hidden layers

Answer

Increase the batch size

Answer

Decrease the number of epochs

Question 10

A data analyst wants to use a model that provides feature importance scores to understand which factors most influence customer churn. They also need the model to handle both numerical and categorical data with minimal preprocessing. Which algorithm is BEST suited?

Accepted Answer

Random forest. Random forests provide feature importance, handle mixed data types, and require little preprocessing.

Answer

Support vector machine (SVM) with RBF kernel

Answer

Logistic regression

Answer

k-nearest neighbours (k-NN)

Question 11

An AI system that can perform any intellectual task that a human being can is referred to as:

Accepted Answer

Artificial General Intelligence (AGI). Artificial General Intelligence (AGI) is the concept of a machine that understands or learns any intellectual task that a human being can.

Answer

Machine learning

Answer

Narrow AI

Answer

Deep learning

Question 12

A research team is fine-tuning a BERT model for a text classification task. They notice that the model's performance on the validation set fluctuates wildly across epochs, sometimes dropping significantly from one epoch to the next. Which technique is MOST likely to stabilise training?

Accepted Answer

Apply gradient clipping. Gradient clipping directly addresses the problem of exploding gradients, which can cause large, destabilizing weight updates during fine-tuning of large models like BERT. By capping the gradient norm (e.g., to a value like 1.0), it prevents a single batch from drastically altering the model's parameters, thus smoothing out validation performance fluctuations across epochs.

Answer

Use a smaller batch size

Answer

Increase the learning rate

Answer

Increase the number of epochs

Question 13

An AI developer is selecting a model architecture for a real-time video surveillance system that must detect objects in each frame and also track movement patterns across frames. Which TWO architectures should the developer combine? (Choose 2)

Accepted Answer

Recurrent neural network (RNN) or LSTM. CNNs are ideal for image feature extraction; RNNs/LSTMs are designed for sequence modelling to track temporal patterns.

Answer

Transformer encoder only

Answer

Generative adversarial network (GAN)

Answer

Variational autoencoder (VAE)

Question 14

A healthcare startup is building a diagnostic support system using a large language model. The system must provide accurate, evidence-based answers and avoid generating harmful or fabricated information. Which THREE techniques should be implemented to achieve this? (Choose 3)

Accepted Answer

Retrieval-Augmented Generation (RAG). RAG grounds answers in retrieved evidence, fine-tuning can align with medical domain, and prompt engineering can enforce accuracy and safety.

Answer

Disabling output filtering to speed up generation

Answer

Increasing the temperature parameter to encourage creativity

Question 15

A machine learning team is splitting a dataset for a binary classification problem. They want to ensure robust evaluation and avoid data leakage. Which TWO practices should they follow? (Choose 2)

Accepted Answer

Split into training, validation, and test sets. Train/validation/test split is standard; cross-validation gives more robust estimates. Shuffling before split prevents ordering bias.

Answer

Normalise the entire dataset before splitting

Answer

Include validation data in the training set for more data

Answer

Use the same split for all experiments