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

Question 1

Which neural network architecture is specifically designed to process sequential data, such as time series or sentences, by maintaining a hidden state that captures information about previous inputs?

Accepted Answer

Recurrent Neural Network (RNN). Recurrent Neural Networks (RNNs) are specifically designed for sequential data because they maintain a hidden state that is updated at each time step, allowing information about previous inputs to persist and influence current and future outputs. This feedback loop makes them ideal for tasks like time series forecasting, natural language processing, and speech recognition, where order and context matter.

Answer

Transformer

Answer

Convolutional Neural Network (CNN)

Answer

Multi-layer Perceptron (MLP)

Question 2

A company wants to automatically group customer support tickets into categories (e.g., billing, technical, account) without pre-labeled data. Which machine learning approach should they use?

Accepted Answer

Unsupervised clustering using K-means. The company has no pre-labeled data, which means supervised learning (which requires labeled examples) is not feasible. Unsupervised clustering, such as K-means, groups data points into clusters based on feature similarity without needing any labels, making it ideal for automatically discovering categories like billing, technical, or account from raw ticket text.

Answer

Supervised classification with logistic regression

Answer

Semi-supervised learning with a small labeled set

Answer

Reinforcement learning with a reward function

Question 3

A team is training a deep learning model for image classification. They observe that training accuracy is high but validation accuracy is low, indicating overfitting. Which TWO techniques should they apply to reduce overfitting? (Select TWO)

Accepted Answer

Use L2 regularization. L2 regularization (also known as weight decay) adds a penalty proportional to the square of the magnitude of the weights to the loss function. This discourages the model from learning overly complex patterns that fit the training data noise, effectively reducing overfitting by keeping weights small and the decision boundary simpler.

Answer

Increase learning rate

Answer

Increase the number of layers

Answer

Reduce training data size

Question 4

A machine learning engineer is training a convolutional neural network (CNN) for object detection in satellite imagery. The training loss is not decreasing significantly. Which TWO adjustments could help the model converge? (Select TWO)

Accepted Answer

Normalize the pixel values to zero mean and unit variance. Normalizing pixel values to zero mean and unit variance (A) ensures that input features have similar scales, which prevents certain weights from updating disproportionately and stabilizes gradient descent. This is especially important for CNNs processing satellite imagery, where raw pixel intensities can vary widely across bands and scenes, leading to poor convergence.

Answer

Remove dropout layers to allow more gradient flow

Answer

Use a smaller batch size to reduce memory

Answer

Increase the learning rate by 10x

Question 5

A data scientist is preparing a dataset for a binary classification model. The dataset has 1000 samples, with 800 positives and 200 negatives. To evaluate the model properly, which THREE steps should they take? (Select THREE)

Accepted Answer

Use a stratified train-test split to preserve class proportions. Stratified train-test splitting ensures that the class distribution (80% positive, 20% negative) is preserved in both training and test sets. This prevents the model from being evaluated on a test set that has a different class ratio, which could give a misleading impression of performance, especially in imbalanced datasets.

Answer

Remove the minority class samples to make the dataset balanced

Answer

Report only accuracy as the evaluation metric

Question 6

A data scientist is building a model to predict whether a loan application will default. The dataset has 10,000 labeled examples with 1,000 defaults. Which metric is MOST appropriate for evaluating this highly imbalanced binary classification?

Accepted Answer

AUC-ROC. AUC-ROC is robust to class imbalance because it measures the trade-off between true positive rate and false positive rate across all thresholds. Accuracy is misleading when classes are imbalanced. Precision and recall focus on one class but are threshold-dependent.

Answer

Precision

Answer

Recall

Answer

Accuracy

Question 7

A company is deploying a large language model for customer support. They want to reduce the number of off-topic or nonsensical responses while maintaining creativity. Which parameter adjustment would BEST achieve this?

Accepted Answer

Decrease temperature to 0.2. Lowering temperature makes the model more deterministic and less likely to produce random outputs. Top-p and top-k can also help but are secondary; temperature directly controls randomness.

Answer

Set top-p to 0.1

Answer

Increase top-k to 100

Answer

Increase temperature to 0.9

Question 8

A startup wants to identify unusual patterns in network traffic to detect potential security breaches. They have a large dataset of normal traffic but very few labeled attacks. Which machine learning approach is MOST suitable?

Accepted Answer

Unsupervised anomaly detection. Unsupervised anomaly detection is the most suitable approach because the startup has a large dataset of normal traffic but very few labeled attacks. This technique learns the baseline of normal behavior from unlabeled data and flags deviations as potential anomalies, which is ideal for detecting unknown or rare attack patterns without requiring labeled attack samples.

Answer

Supervised classification with logistic regression

Answer

Reinforcement learning

Answer

Semi-supervised learning

Question 9

A research team is training a deep learning model for image classification using a small dataset of 1,000 labeled images. They are concerned about overfitting. Which combination of regularisation techniques would be MOST effective?

Accepted Answer

Dropout with a rate of 0.5 and L2 regularisation. Dropout randomly disables neurons during training to prevent co-adaptation, and L2 regularisation penalises large weights. Both are standard regularisation techniques. L1 promotes sparsity but is less common for dense layers. Batch normalisation helps convergence but is not primarily a regularisation method.

Answer

Use early stopping without any other regularisation

Answer

L1 regularisation and batch normalisation

Answer

Increase learning rate and use momentum

Question 10

A developer is building a natural language processing system to classify customer reviews as positive, neutral, or negative. They have 50,000 labeled reviews. Which model architecture is MOST appropriate for this task?

Accepted Answer

Fine-tune a pre-trained BERT model. Fine-tuning a pre-trained BERT model is most appropriate because BERT is a transformer-based model pre-trained on a large corpus and can be fine-tuned on the 50,000 labeled reviews to achieve high accuracy with relatively little data. It captures bidirectional context, which is crucial for sentiment classification, and avoids the need for training from scratch.

Answer

Use a convolutional neural network (CNN) on raw text

Answer

Train a recurrent neural network (RNN) from scratch

Answer

Word2vec embeddings followed by logistic regression

Question 11

A company wants to recommend products to users based on their past purchase history. Which machine learning paradigm is BEST suited for this task?

Accepted Answer

Supervised learning with regression. Recommender systems are a classic application of supervised learning (if using regression or classification to predict ratings) or unsupervised learning (collaborative filtering). Among the options, supervised learning with regression is appropriate for predicting purchase likelihood.

Answer

Reinforcement learning

Answer

Unsupervised clustering

Answer

Self-supervised learning

Question 12

A team is training a generative adversarial network (GAN) to generate realistic images of furniture. The generator loss decreases sharply while the discriminator loss increases. What is the MOST likely issue and recommended action?

Accepted Answer

The generator is too strong; train the discriminator more frequently. If the generator loss drops too fast and discriminator loss rises, the generator is overpowering the discriminator. The typical remedy is to train the discriminator more often (e.g., 5 steps per generator step) or adjust the learning rates.

Answer

Mode collapse has occurred; increase the generator's learning rate

Answer

The discriminator is overfitting; decrease its capacity

Answer

The learning rates are too high; reduce both

Question 13

An AI practitioner needs to extract key phrases from a large collection of customer support emails for trend analysis. Which technique is MOST suitable?

Accepted Answer

Named entity recognition (NER). Named entity recognition (NER) is the most suitable technique because it automatically identifies and extracts predefined entities such as names, dates, product names, and other key phrases from text. This directly supports extracting key phrases from customer support emails for trend analysis. Other techniques like language translation, text classification, and sentiment analysis do not focus on extracting specific phrases.

Answer

Language translation

Answer

Text classification

Answer

Sentiment analysis

Question 14

A data scientist is selecting a model for a binary classification task where interpretability is critical because of regulatory requirements. The dataset has 20 features and 10,000 samples. Which model is MOST appropriate?

Accepted Answer

Decision tree. Decision trees are inherently interpretable, showing the decision rules. Random forests and gradient boosting are ensembles that sacrifice interpretability for accuracy. Neural networks are black-box models.

Answer

Neural network (MLP)

Answer

Gradient boosting machine

Answer

Random forest classifier

Question 15

A developer is using a pre-trained BERT model for a question-answering system. They want to ensure the model can handle out-of-vocabulary words. Which component of the BERT architecture is responsible for this?

Accepted Answer

WordPiece tokenisation. WordPiece tokenisation is the component of BERT that handles out-of-vocabulary (OOV) words by breaking them into subword units (e.g., 'playing' → 'play' + '##ing'). This allows the model to represent any word, even unseen ones, as a sequence of known subword tokens, ensuring no word is truly out of vocabulary.

Answer

Positional encoding

Answer

Feed-forward layers

Answer

Attention mechanism