hw10_concept
docx
keyboard_arrow_up
School
Parkland College *
*We aren’t endorsed by this school
Course
251
Subject
Industrial Engineering
Date
Jan 9, 2024
Type
docx
Pages
3
Uploaded by ChancellorFlowerSquirrel33
Homework 10
Instructions
This homework contains
2
concepts and
3
programming questions. In MS word or a similar text
editor, write down the problem number and your answer for each problem. Combine all answers
for concept questions in a single PDF file. Export/print the Jupyter notebook as a PDF file
including the code you implemented and the outputs of the program. Make sure all plots and
outputs are visible in the PDF.
Combine all answers into a single PDF named andrewID_hw10.pdf and submit it to Gradescope
before the due date. Refer to the syllabus for late homework policy. Please assign each question a
page by using the “Assign Questions and Pages” feature in Gradescope.
Here is a breakdown of the points for programming questions:
Name
Points
M10-L1-P1
15
M10-L2-P1
15
M10-HW1
60
Problem 1 (5 points)
The two linear least squares regression models are fit on the same exact training and validation
datasets. Below are the R
2
plots for the two models. Which of the following can be said about the
models?
(Multiple choice - choose one)
1.
Model 1 is low bias but high variance, Model 2 is low variance but high bias
2.
Model 1 is high bias but low variance, Model 2 is high variance but low bias
3.
Model 1 is low bias but high variance, Model 2 is high bias
4.
Model 1 is high bias but low variance, Model 2 is high variance
Problem 2 (5 points)
Which of the following statements is true of k-fold cross validation?
Multiple choice (choose one)
1.
K-fold cross validation helps us determine how to partition the data to obtain optimal
model performance
2.
K-fold cross validation trains k individual models and combines their predictions to
generate a better performing model
3.
K-fold cross validation trains k models to find the optimal set of hyperparameters for a
given dataset
4.
K-fold cross validation partitions the data into k equal sized subsets, and trains k models,
each time using one subset as the validation data and the rest as the training data
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