Crowdly

Add to Chrome

Machine Learning: Theory and Practice-Lecture,Section-1-Fall 2025

Looking for Machine Learning: Theory and Practice-Lecture,Section-1-Fall 2025 test answers and solutions? Browse our comprehensive collection of verified answers for Machine Learning: Theory and Practice-Lecture,Section-1-Fall 2025 at moodle.nu.edu.kz.

Get instant access to accurate answers and detailed explanations for your course questions. Our community-driven platform helps students succeed!

A classifier outputs predictions for 3 classes (A, B, C). The confusion matrix is:

CM=[305032520228]

\text{CM} =

\begin{bmatrix}

30 & 5 & 0 \\

3 & 25 & 2 \\

0 & 2 & 28

\end{bmatrix}

Where rows = true labels, columns = predicted labels.

What is the recall for class B?

0.8333

0.8929

0.7895

View this question

Metric	Definition	Python Command
A) Accuracy	1. Correct positive predictions out of all predicted positives	`accuracy_score(y_true, y_pred)`
B) Precision	2. Overall correctness of the model	`precision_score(y_true, y_pred)`
C) Recall	3. Harmonic mean of precision and recall	`recall_score(y_true, y_pred)`
D) F1-Score	4. Correct negative predictions out of all actual negatives	`f1_score(y_true, y_pred)`
E) Specificity	5. Correct positive predictions out of all actual positives	`TN / (TN + FP)`

A-2, B-1, C-5, D-4, E-3

A-2, B-1, C-5, D-3, E-4

A-2, B-5, C-1, D-3, E-4

A-1, B-2, C-3, D-4, E-5

View this question

Which of the following correctly describes the sequence and purpose of steps in Linear Discriminant Analysis (LDA)?

Compute class means → compute overall mean → compute within-class scatter → compute between-class scatter → solve generalized eigenvalue problem → sort eigenvalues → form projection matrix → project data.

Compute eigenvectors first → compute class means → compute overall mean → form projection matrix → compute scatter matrices → project data → sort eigenvalues.

Compute the overall mean → compute class means → compute within-class scatter → compute between-class scatter → solve generalized eigenvalue problem → sort eigenvalues → form projection matrix → project data.

Compute within-class scatter → compute between-class scatter → compute class means → compute overall mean → solve eigenvalue problem → sort eigenvalues → project data → form projection matrix.

View this question

Match the followings:

Training accuracy: 99%, Test accuracy: 60%

Training accuracy: 40%, Test accuracy: 38%

Training accuracy: 95%, Test accuracy: 93%

Training accuracy: 50%, Test accuracy: 49%

View this question

Which of the following correctly matches the machine learning paradigm with its example?

Unsupervised Learning – Predicting house prices from past sales data

Reinforcement Learning – Training a robot to walk by trial and error

Semi-Supervised Learning – Classifying emails using only labeled data

Supervised Learning – Grouping customers by purchasing behavior

View this question

Which of the following best describes Stochastic Gradient Descent (SGD)?

Parameters are updated without computing gradients, by directly adjusting weights toward the minimum.

Parameters are updated only once per epoch, after computing gradients on a mini-batch.

B) Parameters are updated after computing the gradient on just one randomly selected training example at a time, leading to faster initial progress but noisy convergence that oscillates near the minimum.

Parameters are updated after computing the gradient using the entire training dataset, leading to stable, deterministic convergence.

View this question

A store sells smartphones of three brands: Brand A: 40% of sales, Brand B: 35% of sales, Brand C: 25% of sales

Defect rates within the first year: Brand A: 15%, Brand B: 10%, Brand C: 20%

What is the probability that a customer buys a Brand B phone and it turns out defective in the first year?

0.040

0.035

0.025

0.10

100%

View this question