AI0-001 Machine Learning and Deep Learning Practice Test 6 — 15 Questions

Question 1

During training of a neural network, the loss oscillates and does not converge smoothly. The learning rate is set to 0.1. What is the most likely cause and what adjustment should be made?

Accepted Answer

Learning rate too high; decrease it. A learning rate of 0.1 is relatively high for many neural network architectures. When the learning rate is too high, the optimizer takes steps that overshoot the minimum of the loss function, causing the loss to oscillate or even diverge instead of converging smoothly. Decreasing the learning rate allows for smaller, more stable weight updates, leading to smoother convergence.

Answer

Learning rate too low; increase it

Answer

Batch size too small; increase it

Answer

Too many epochs; stop early

Question 2

A team is building a model to predict stock prices based on time series data. They need to capture long-term dependencies and avoid vanishing gradients. Which architecture is best suited?

Accepted Answer

LSTM. LSTM (Long Short-Term Memory) networks are specifically designed to capture long-term dependencies in sequential data through their gating mechanisms (input, forget, and output gates), which regulate the flow of information and mitigate the vanishing gradient problem that plagues standard RNNs. This makes them ideal for time series forecasting tasks like stock price prediction, where historical context over many time steps is critical.

Answer

Standard RNN

Answer

Autoencoder

Answer

CNN

Question 3

Which TWO are characteristics of supervised learning?

Accepted Answer

Requires labeled data. Option B is correct because supervised learning fundamentally requires a labeled dataset, where each training example is paired with a known target (ground-truth) value that the model learns to map inputs to. Option E is correct because supervised models are trained to predict an output that is either continuous (regression, e.g., predicting a price) or categorical (classification, e.g., predicting a class label). Option A is incorrect because the absence of a target variable describes unsupervised learning, not supervised learning. Option C is incorrect because reinforcement signals (rewards/penalties from an environment) characterize reinforcement learning, a separate paradigm. Option D is incorrect because clustering is an unsupervised task that discovers structure without labeled targets.

Answer

Does not require target variable

Answer

Uses reinforcement signals

Answer

Learns to cluster data

Question 4

Which THREE techniques can help reduce overfitting in neural networks?

Accepted Answer

Increasing training data size. Increasing the training data size helps reduce overfitting by providing the model with more examples to learn from, which reduces the variance and improves generalization. With more data, the model is less likely to memorize noise and instead learns the underlying patterns, making it more robust on unseen data.

Answer

Using a larger learning rate

Answer

Increasing number of layers

Question 5

Which TWO are key differences between Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN)?

Accepted Answer

RNNs have internal memory; CNNs do not. RNNs possess a hidden state that acts as internal memory, allowing them to retain information from previous time steps, which is essential for processing sequential data. In contrast, CNNs lack this internal memory mechanism; they process inputs independently without maintaining a state across different inputs, making them unsuitable for tasks requiring temporal context.

Answer

CNNs are designed for sequential data; RNNs for spatial data

Answer

CNNs can handle variable-length inputs; RNNs require fixed-size inputs

Answer

CNNs use backpropagation; RNNs do not

Question 6

Refer to the exhibit. What is the most likely issue and what action should be taken?

Accepted Answer

Overfitting; apply early stopping around epoch 15. The training loss continues to decrease while the validation loss starts to increase after approximately epoch 15, which is a classic sign of overfitting. The model is memorizing the training data rather than generalizing, so applying early stopping around epoch 15 would prevent further divergence and preserve the best validation performance.

Answer

Learning rate is too low; increase it

Answer

Underfitting; increase model complexity

Answer

Data imbalance; use class weights

Question 7

Refer to the exhibit. What is the recall of the model?

Accepted Answer

0.44. Recall is calculated as True Positives divided by (True Positives + False Negatives). From the confusion matrix in the exhibit, True Positives = 400 and False Negatives = 500, so recall = 400 / (400 + 500) = 400 / 900 ≈ 0.44. Option A is correct because this matches the computed recall value.

Answer

0.80

Answer

0.90

Answer

0.99

Question 8

A data scientist trains a linear regression model on housing prices. The training error is low, but test error is high. What is the most likely issue?

Accepted Answer

Overfitting. Low training error combined with high test error is the classic symptom of overfitting, where the model has memorized the training data, including its noise, rather than learning the underlying patterns. This causes the model to perform poorly on unseen data, which is exactly what the high test error indicates.

Answer

Multicollinearity

Answer

Data leakage

Answer

Underfitting

Question 9

A company uses a neural network for fraud detection. The dataset has 99% legitimate, 1% fraudulent. The model achieves 99% accuracy but fails to detect most frauds. Which metric should they focus on?

Accepted Answer

Recall. Recall (sensitivity) measures the proportion of actual positives correctly identified. In this fraud detection scenario with 99% legitimate and 1% fraudulent transactions, a 99% accuracy can be achieved by simply predicting all transactions as legitimate, which yields 0% recall for the fraud class. Focusing on recall ensures the model captures the majority of fraudulent cases, addressing the critical failure to detect fraud despite high accuracy.

Answer

Precision

Answer

F1-score

Answer

AUC-ROC

Question 10

A data scientist wants to reduce the dimensionality of a dataset with 200 features before training a regression model. Which technique should they use?

Accepted Answer

PCA. PCA (Principal Component Analysis) is the correct technique because it is an unsupervised linear dimensionality reduction method that identifies the directions (principal components) of maximum variance in the data. For a dataset with 200 features, PCA can reduce dimensionality while preserving as much variance as possible, which is ideal before training a regression model to avoid overfitting and multicollinearity.

Answer

LDA

Answer

t-SNE

Answer

Autoencoder

Question 11

An organization needs to classify customer emails into categories. They have labeled data for some categories but not all. Which approach should they use?

Accepted Answer

Semi-supervised learning. Semi-supervised learning (D) is the correct approach because the organization has labeled data for some categories but not all. This technique leverages a small amount of labeled data to guide the clustering or classification of a larger pool of unlabeled data, effectively combining supervised and unsupervised methods to handle partially labeled datasets.

Answer

Unsupervised clustering then labeling

Answer

Supervised learning for all categories

Answer

Reinforcement learning

Question 12

A machine learning engineer notices that the gradient values in a deep network are becoming extremely small during backpropagation. What is this problem?

Accepted Answer

Vanishing gradient. The vanishing gradient problem occurs when gradients become extremely small during backpropagation, especially in deep networks with many layers. This causes the weights in earlier layers to update very slowly or not at all, severely hindering training. The correct answer is D because the scenario directly describes the hallmark symptom of vanishing gradients.

Answer

Dead ReLU

Answer

Exploding gradient

Answer

Covariate shift

Question 13

A team wants to predict monthly sales using historical data. Which algorithm is most appropriate?

Accepted Answer

Linear regression. Linear regression is the most appropriate algorithm because the goal is to predict a continuous numerical value (monthly sales) based on historical data. It models the relationship between input features and the target variable by fitting a linear equation, making it ideal for regression tasks where the output is a real number.

Answer

K-means

Answer

Decision tree

Answer

Logistic regression

Question 14

A model trained on a dataset has high bias and low variance. What does this indicate?

Accepted Answer

Underfitting. High bias and low variance indicate that the model is too simple to capture the underlying patterns in the data, leading to systematic errors on both training and test sets. This is the classic signature of underfitting, where the model fails to learn the training data adequately.

Answer

Good fit

Answer

Data leakage

Answer

Overfitting

Question 15

Which TWO are evaluation metrics for classification problems? (Choose two.)

Accepted Answer

Precision. Precision is a classification metric that measures the proportion of true positive predictions among all positive predictions made by the model. It is calculated as TP / (TP + FP) and is critical when the cost of false positives is high, such as in spam detection or fraud alert systems.

Answer

Mean Absolute Error

Answer

R-squared

Answer

Mean Squared Error