CSCI 5521辅导、辅导Java，Python程序
- 首页 >> Algorithm 算法 CSCI 5521: Machine Learning Fundamentals (Spring 2022)
Quiz 1 (Thursday, Feb 10)
Due on Gradescope at 02:00 PM, Friday, Feb 11
Instructions:
This quiz has 3 questions, 30 points, on 1 page.
Please write your name & ID on your submission pages.
1. (6 points) Supervised learning has a wide range of applications. For example, one can define
a robot (vs non-robot) based on a number of traits. Please model the question as a two-class
classification task and answer the following questions.
(a) Name two relevant features to this two-class classification task. (Any reasonable features are
acceptable).
(b) What are the labels in this two-class classification task?
2. (10 points) What could we do to reduce overfitting in a polynomial regression model? Select all
the option(s) that apply.
(a) Decrease polynomial degree.
(b) Change to a more complex model (e.g., a model with more parameters).
(c) Add new training data and keep test data the same.
(d) Add new test data and keep training data the same.
(e) Sample half of the original training data as new training data.
3. (14 points) The conditional probability density functions of two classes C1 and C2 are shown in
the figure below, with P (x|C1) ～ N (0, 1) and P (x|C2) ～ N (2, 1.2).
(a) Assuming the priors are equal, predict which class (C1 or C2) the data point x = 1.5 (illus-
trated with the green dot) belongs to. Briefly explain why.
(b) What if the priors are P (C1) = 0.9 and P (C2) = 0.1, respectively? (Note: High-level
explanation is good, but you can use formulations if it helps explain).
Quiz 1 (Thursday, Feb 10)
Due on Gradescope at 02:00 PM, Friday, Feb 11
Instructions:
This quiz has 3 questions, 30 points, on 1 page.
Please write your name & ID on your submission pages.
1. (6 points) Supervised learning has a wide range of applications. For example, one can define
a robot (vs non-robot) based on a number of traits. Please model the question as a two-class
classification task and answer the following questions.
(a) Name two relevant features to this two-class classification task. (Any reasonable features are
acceptable).
(b) What are the labels in this two-class classification task?
2. (10 points) What could we do to reduce overfitting in a polynomial regression model? Select all
the option(s) that apply.
(a) Decrease polynomial degree.
(b) Change to a more complex model (e.g., a model with more parameters).
(c) Add new training data and keep test data the same.
(d) Add new test data and keep training data the same.
(e) Sample half of the original training data as new training data.
3. (14 points) The conditional probability density functions of two classes C1 and C2 are shown in
the figure below, with P (x|C1) ～ N (0, 1) and P (x|C2) ～ N (2, 1.2).
(a) Assuming the priors are equal, predict which class (C1 or C2) the data point x = 1.5 (illus-
trated with the green dot) belongs to. Briefly explain why.
(b) What if the priors are P (C1) = 0.9 and P (C2) = 0.1, respectively? (Note: High-level
explanation is good, but you can use formulations if it helps explain).