AI0-001 Machine Learning and Deep Learning Practice Test 4 — 15 Questions

Question 1

A team is designing a deep learning pipeline for a computer vision task. They want to reduce overfitting. Which two techniques are specifically effective for this purpose? (Select TWO.)

Accepted Answer

Dropout. Options A and B are correct. Dropout randomly drops neurons during training, preventing co-adaptation. L2 regularization adds a penalty on weights, discouraging complexity. Option C, increasing learning rate, can hinder convergence. Option D, adding more layers, typically increases overfitting. Option E, smaller batch size, can have a regularizing effect but is not as direct or commonly cited as the primary techniques.

Answer

Using a smaller batch size

Answer

Adding more layers

Answer

Increasing the learning rate

Question 2

A data scientist is using an ensemble method to combine multiple models. Which three statements about bagging (Bootstrap Aggregating) are true? (Select THREE.)

Accepted Answer

It reduces variance without increasing bias. Options A, B, and D are correct. Bagging reduces variance of unstable models (like trees) without increasing bias (A). It trains models independently on bootstrap samples (B). Random forests use bagging along with random feature selection (D). Option C is false because boosting reduces bias, not bagging. Option E is false because bagging typically uses the same type of base model.

Answer

It requires the base models to be of different types

Answer

It reduces the error by combining weak learners

Question 3

Refer to the exhibit. The training log shows losses and accuracies over 5 epochs. What is the most likely problem?

Accepted Answer

Overfitting. Option B is correct because training loss decreases while validation loss increases, a classic sign of overfitting. Option A is incorrect because underfitting would show high losses on both sets. Option C is incorrect because vanishing gradient affects training loss progression, not divergence. Option D is incorrect because data leakage typically causes both sets to perform well.

Answer

Data leakage

Answer

Underfitting

Answer

Vanishing gradient

Question 4

Refer to the exhibit. A developer is using the above configuration for a multi-class classification task. The model performs well on training data but poorly on validation data. Which modification could help?

Accepted Answer

Add L2 regularization to the dense layers. Option B is correct because adding L2 regularization to the dense layers penalizes large weights, reducing overfitting. Option A is incorrect because increasing dropout from 0.5 may hurt performance; it's already a reasonable value. Option C is incorrect because increasing learning rate could destabilize training. Option D is incorrect because removing dropout would likely increase overfitting.

Answer

Remove dropout

Answer

Increase the dropout rate

Answer

Increase the learning rate

Question 5

Refer to the exhibit. The training pod is using 2 GPUs. During training, the GPU utilization is only 30% each. What is the most likely cause?

Accepted Answer

The batch size is too small to fully utilize GPUs. Option A is correct because a batch size of 32 is small for two GPUs, leading to underutilization as GPUs spend time on kernel launches and synchronization. Option B is incorrect because learning rate does not directly impact GPU utilization. Option C is incorrect because number of epochs does not affect utilization per step. Option D is incorrect because missing CUDA would cause errors, not low utilization.

Answer

The learning rate is too high

Answer

The image is missing CUDA libraries

Answer

The number of epochs is too high

Question 6

A data scientist needs to predict whether a customer will churn based on historical data containing features like account age, monthly charges, and support tickets. The target variable is binary (churn or not). Which type of machine learning algorithm should be used?

Accepted Answer

Logistic regression. Logistic regression is a classification algorithm well-suited for binary outcomes. Linear regression is for continuous outputs, K-means is unsupervised, and PCA is dimensionality reduction.

Answer

Linear regression

Answer

K-means clustering

Answer

Principal component analysis

Question 7

A team trained a deep neural network on a limited dataset. The training loss decreases consistently, but the validation loss starts increasing after 20 epochs. What is the most likely issue and the best corrective action?

Accepted Answer

Overfitting; apply regularization like dropout. The divergence between training and validation loss indicates overfitting. Regularization techniques like dropout help reduce overfitting.

Answer

Vanishing gradient; use ReLU activation

Answer

Underfitting; increase model complexity

Answer

Data leakage; reshuffle split

Question 8

A company is building a computer vision system to detect defects in manufactured parts. They have 10,000 labeled images per class (defective and non-defective). They want to achieve high accuracy with limited computational resources. Which deep learning architecture and approach is most appropriate?

Accepted Answer

Use a pre-trained VGG16 and fine-tune the last few layers. Transfer learning using a pre-trained CNN like VGG16, fine-tuning only the last few layers, leverages existing features and reduces training time and resource requirements.

Answer

Train a custom CNN from scratch with many layers

Answer

Use a decision tree ensemble

Answer

Use an RNN to process image sequences

Question 9

A machine learning engineer has a dataset of 100,000 records. She splits it into 70% training, 15% validation, and 15% test sets. After training, the model achieves 95% accuracy on training and 85% on validation. What does the accuracy difference most likely indicate?

Accepted Answer

The model is overfitting. A wide gap between training and validation accuracy is a classic sign of overfitting, where the model memorizes training data but fails to generalize.

Answer

The validation set is too small

Answer

The model generalizes well

Answer

The test set should be larger

Question 10

A deep learning model for sentiment analysis uses a softmax output layer. The hidden layers currently use tanh activation. Which activation function should replace tanh to mitigate vanishing gradients in deeper networks?

Accepted Answer

ReLU. ReLU does not saturate for positive values, helping avoid vanishing gradient issues common with tanh and sigmoid.

Answer

Sigmoid

Answer

Softmax

Answer

Linear

Question 11

A fraud detection model is trained on a dataset where only 0.1% of transactions are fraudulent. The model achieves 99.9% accuracy but fails to catch most frauds. Which metric should the team prioritize, and which technique could help?

Accepted Answer

Precision-Recall AUC; use oversampling like SMOTE. With severe class imbalance, accuracy is misleading. Precision-Recall AUC focuses on minority class, and SMOTE oversamples it.

Answer

Mean Squared Error; use L2 regularization

Answer

F1 score; use principal component analysis

Answer

Accuracy; collect more data

Question 12

A dataset contains features on vastly different scales (e.g., age 0-100 vs. income 0-1,000,000). Which preprocessing step is essential before training a neural network?

Accepted Answer

Feature scaling (standardization or normalization). Neural networks are sensitive to feature scale; standardization or normalization ensures stable convergence.

Answer

Data augmentation

Answer

Dimensionality reduction

Answer

One-hot encoding

Question 13

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 that is too high causes the optimizer to overshoot minima, leading to oscillations. Reducing the learning rate stabilizes training.

Answer

Learning rate too low; increase it

Answer

Batch size too small; increase it

Answer

Too many epochs; stop early

Question 14

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 networks are designed with gating mechanisms to capture long-range dependencies and mitigate vanishing gradient problems in standard RNNs.

Answer

Standard RNN

Answer

Autoencoder

Answer

CNN

Question 15

Which TWO are characteristics of supervised learning?

Accepted Answer

Requires labeled data. Supervised learning requires labeled data and predicts either continuous (regression) or categorical (classification) outputs.

Answer

Does not require target variable

Answer

Uses reinforcement signals

Answer

Learns to cluster data