Quiz 1

.docx

School

Georgia Institute Of Technology *

*We aren’t endorsed by this school

Course

6740

Subject

Industrial Engineering

Date

Apr 3, 2024

Type

docx

Pages

Uploaded by lindawangnn

Quiz 1 Question 1 1/1pts In supervised learning, when we utilize the training data to estimate the function h (21, .., x,) to predict the response Y from the additive noise model, Y = h(z1, -+, 2p) + € which of the following statement is correct on the role of the additive noise model? It might or might not be the true underlying model that generates the data. It is the true generative model.

Question 2 1/1pts In the K-nearest neighborhood (KNN) algorithm, is it true that the best choice of K neighbors is K=1? No, the choice of K depends on the context and applications, and can be tuned via cross validation. esponding training erroi

Questions 3-5 are based on the following materials. A GT student was asked to find the weights of two balls, A and B, using a scale with random measurement errors. When the student measured one ball at a time, the weights of A and B were 3 Ibs and 4 Ibs. However, if the student measured both balls simultaneously, then the total weight (A+B) was 6 Ibs. The poor student was confused, and decided to measure (A+B) one more time. The new observed weight of (A+B) is still 6 Ibs. For your information, the observed weights are summarized in the following table: A B A+B First Time 3 4 6 Second Time 6 In addition, some cutoff values for the t-distribution might be useful below: V= v=3 v=4 v=>5 tois, 1386 1250 |1.190 |1.156 t0.30,0 0.617 0.584 0.569 0.559

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