Quiz2

.pdf

School

Arizona State University *

*We aren’t endorsed by this school

Course

589

Subject

Electrical Engineering

Date

May 18, 2024

Type

pdf

Pages

2

Uploaded by BrigadierLlamaPerson924

EEE 589: Machine Learning Course Quiz 2 Instructions Answer the following questions. Show all work for full credit. Write your an- swers clearly and concisely. Questions 1. (10 points) Explain the concept of regularization in machine learning. Compare and contrast L1 (Lasso) and L2 (Ridge) regularization. 2. (10 points) Describe the process of feature selection. Why is it important in building machine learning models? 3. (10 points) Given the following confusion matrix for a binary classifica- tion problem, calculate the accuracy, precision, recall, and F1-score. Predicted Positive Predicted Negative Actual Positive 50 10 Actual Negative 5 35 4. (10 points) What is the difference between batch gradient descent and stochastic gradient descent? In what scenarios would you prefer one over the other? 5. (10 points) Explain the concept of decision boundaries in the context of classification algorithms. Provide an example using a linear classifier. 6. (10 points) Describe the role of the learning rate in gradient descent optimization. What are the potential consequences of choosing a learning rate that is too high or too low? 7. (10 points) Explain the principle of the Support Vector Machine (SVM) algorithm. What is the significance of the margin in SVM? 8. (10 points) Define and explain the term ”dimensionality reduction”. De- scribe two techniques for dimensionality reduction. 1
9. (10 points) What are the main differences between bagging and boosting methods in ensemble learning? 10. (10 points) Discuss the challenges of working with imbalanced datasets. What techniques can be used to address these challenges? Bonus Question 1. (5 points) Explain the concept of the ROC curve and the AUC metric. How are they used to evaluate the performance of a binary classifier? 2
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help