Ask Question, Ask an Expert

+1-415-315-9853

info@mywordsolution.com

Ask DBMS Expert


Home >> DBMS

problem 1) Categorical variable tread Pattern = {A, B} and numerical variable tread Depth are used to classify Handling = {good, poor} of a vehicle. Depth is normally distributed with mean 9 and standard deviation 3 when Handling is good and mean 16 and standard deviation 4 when Handling is poor.

There are 300 rows of data for training and the number of rows of data for each combination of Pattern and Handling are given in the table below.

1228_pattern and handling.jpg

Given row x0 = (Pattern = A, Depth=12). Use a naive Bayes’ classifier to compute the class of Handling assigned to x0. Show your work for full credit.

problem 2) Consider the following neural network for two predictors Thickness and Alignment and two classes Print Quality High and Low. Some weights are shown in the table, including weights for constant (threshold) nodes that link to each output node.

1751_neural network.jpg

Suppose input data row x0 produces z1 = 0.5 at node H1 and z2 = 0.4 at node H2. Assume the softmax function is used at the outputs. Compute the output at each output node. To what Print Quality class is row x0 assigned?

problem 3) In either the design or training of a neural network, provide a list of several ways to reduce the complexity of the model.

problem 4) Consider a support vector machine with three inputs x1, x2, and x3. Assume there are only two support vectors with values and parameters as follows:

405_vector machine.jpg

problem 5) Consider one versus the rest voting used for classifier with three classes {a, b, c}. Given a row of data denoted as x0 suppose that the classifier for a versus the rest predicts the rest, b versus the rest predicts the rest, and c versus the rest predicts c. What are the votes for each class for x0?

158_classifier.jpg

problem 6) Consider the data with categorical predictor x1 = {green or red} and numerical predictor x2 and the class variable y shown in the following table. The weights for a round of boosting are also shown in the table. Suppose the classifier built from this round of boosting assigns y = 1 for x2 < 0.45 and y = -1 for x2 > 0.45. Compute the coefficient α for this classifier in the boost algorithm.

425_categorical predictor.jpg

problem 7) A data set with 1000 rows is input to a neural network in Weka. The test option is set to 10-fold cross validation and the neural network option validationSetSize = 20%. How many rows of data are used in a validation set in a fold?

A support vector machine in Weka uses a Gaussian (radial basis function) kernel with parameter gamma. Gamma should be selected less than or equal to one. Circle True or False.

A support vector machine in Weka uses a Gaussian (radial basis function) kernel with parameter gamma = 0.2. This corresponds to the parameter σ2 equal to what value?

problem 8) Given a dataset with 1000 rows and 25 predictors labeled x1, x2, …,x25 to classify into two classes {a, b}. Consider the small random forest with 3 trees and one split in each tree as shown below. Here 5 predictors are selected randomly at each node. The class assigned to each leaf node is also shown.

2343_dataset.jpg

a) Given a row of data x0 with x1= green, x5 = 4, x9 = 9, predict the class label for the row.

b) For Tree1, it can be concluded that the best split among all 25 predictors is obtained from x1. Circle True or False.

c) Approximately 368 rows are expected to be out of bag for Tree 1. Circle True or False.

d) Categorical variables are coded to {0, 1} indicator variables in a random forest. Circle True or False.

problem 9) Suppose the random sample used for each tree in the previous random forest is decreased from 1000 rows to 500 rows. Circle ALL that are true for the ensemble classifier.

a) Variance of predictions is expected to decrease.

b) Bias of predictions is expected to decrease.

c) Each base classifier is expected to have more out of bag rows of data.

d) Generalization error is expected to decrease.

problem 10) A Bayesian network is shown for the variables paper Thickness, paper Alignment and Print Quality. The conditional probabilities are provided in the tables beside the nodes. Here, Thickness = {high or low}, Alignment = {straight or angled}, and Print Quality = {good or bad}.

1930_bayesian network.jpg

find out the following quantities from the information in the Bayesian network.

a) P(Alignment = straight)

b) P(Alignment = straight | Print Quality = good)

DBMS, Programming

  • Category:- DBMS
  • Reference No.:- M9377

Have any Question? 


Related Questions in DBMS

Query 1list all movies played in landmark or music box

Query 1 List all movies played in Landmark or Music Box. Output only titles and eliminate duplicates. Query 2 List all stars born after 1960. Order them by their birthdate in ascending order. Output their first names, la ...

Assignment advanced relational databaseproject- advance

Assignment: Advanced Relational Database PROJECT- Advance SQL Overview: Using the knowledge garnered thus far, please solve all of the below problems. Please run the attached SQL script file at the SQL*PLUS prompt. This ...

Taskoverview of business casealive amp boating aampb is a

Task Overview of business case: Alive & Boating (A&B) is a small start­up company that sells small boats in Wagga. A&B keeps its models in several showrooms across the city. At this stage customers cannot view the availa ...

Ngocbo database projectthe purpose of this project is to

NGO/CBO Database Project The purpose of this project is to build a database to store and retrieve basic information on NGOs/CBOs collected through a questionnaire given in the Appendix. Database Specifications In view of ...

Data analysis assignment- apriori analysis and cluster

Data Analysis assignment- ApriorI analysis and Cluster analysis CLUSTER ANALYSIS The purpose of this assignment is to demonstrate steps performed in a K-Means Cluster analysis. Review the "k-MEANS CLUSTERING ALGORITHM" s ...

How up-to-date should data warehouse information

HOW UP-TO-DATE SHOULD DATA WAREHOUSE INFORMATION BE? Information timeliness is a must in a data warehouse-old and obsolete information leads to poor decision making. Below is a list of decision-making processes that peop ...

Enterprisebim projectgoal - to enable students to

Enterprise/BIM Project Goal - To enable students to experience the process of building a non-trivial database-backed web application. Tasks 1. Choose any area that interests you - this does not necessarily have to be abo ...

Projectfalcor supplies is a distributor of high tech

Project Falcor Supplies is a distributor of high tech teaching equipment. Its primary target customers are schools in the region who purchase the teaching equipment for classrooms and online use. The company's main compe ...

Use sql management studio to create a database called

Use SQL Management Studio to create a database called ITCO630_P1.MDF. Be sure to store the database in a location that you will remember. Add the following tables and data to the database. Use the appropriate field types ...

Exercise 1 - html and Exercise 1 - HTML and XML ID Name Stars Facilities Address Distance

Exercise 1 - HTML and XML ID Name Stars Facilities Address Distance from center (KM) Available 1 Les Jardins du Marais 3 Internet 74 rue Amelot, Paris, 75011 2 True 2 Golden Tulip Little Palace 4 Internet Gym Parking Res ...

  • 4,153,160 Questions Asked
  • 13,132 Experts
  • 2,558,936 Questions Answered

Ask Experts for help!!

Looking for Assignment Help?

Start excelling in your Courses, Get help with Assignment

Write us your full requirement for evaluation and you will receive response within 20 minutes turnaround time.

Ask Now Help with Problems, Get a Best Answer

WalMart Identification of theory and critical discussion

Drawing on the prescribed text and/or relevant academic literature, produce a paper which discusses the nature of group

Section onea in an atwood machine suppose two objects of

SECTION ONE (a) In an Atwood Machine, suppose two objects of unequal mass are hung vertically over a frictionless

Part 1you work in hr for a company that operates a factory

Part 1: You work in HR for a company that operates a factory manufacturing fiberglass. There are several hundred empl

Details on advanced accounting paperthis paper is intended

DETAILS ON ADVANCED ACCOUNTING PAPER This paper is intended for students to apply the theoretical knowledge around ac

Create a provider database and related reports and queries

Create a provider database and related reports and queries to capture contact information for potential PC component pro