What would be the cost for this assignment?
ADS 526 Machine Learning II Semester/Year/Beginning and end dates of course: Summer II 2021 August 30, 2021 –October 23, 2021 Professor: Xiaoxia Liu Office: Office Hours: Online, by appointment Telephone: (770) 712-4978 (cell) Email:
[email protected] Prerequisites M EXT 099 recommended for remote students. Course Credits: 3 Department Chair Xiaoxia Liu Chair Contact Information
[email protected] COURSE DESCRIPTION The goal of this course is to continue introducing various machine learning methods which are developed in last few years and widely used in all industries. Built upon finishing Machine Learning I ADS525, this course will introduce other commonly used machine learning models and apply them to different datasets. The topics in this course include logistic regression, discriminant analysis, support vector machines, tree-based methods, principal component analysis and clustering analysis. The course emphasizes on helping students understand the concepts and ideas of some modern statistical learning methods and apply these methods to various studies and industries. Implementation different methods with R software will be introduced whenever appropriate. STUDENT LEARNING OUTCOME Students will: After completing the course, a student will be able to · Understand the concepts and ideas of various machine learning methods · Grasp the statistical principles behind these methods and understand their pros and cons; · Implement these methods in software packages and use them in practice. Course Prerequisites · ADS 522 Introduction to Data Analytics and ADS 534 Statistical Modeling · ADS 525 Machine Learning I · Working experience with R software. REQUIRED COURSE MATERIAL · Textbook: James, Witten, Hatie, Tibshirani (2013). An Introduction to Statistical Learning with Application in R. Springer. [free PDF available online] · Recommended Readings: Hastie, Tibshirani, and Friedman (2009). The Elements of Statistical Learning, Second edition. Springer. [free PDF available online, much more advanced reference book] Hastie, Tibshirani, and Wainwright (2015). Statistical Learning with Sparsity: The Lasso and Generalizations. CRC. Efron and Tibshirani (1993). An Introduction to the Bootstrap. Chapman & Hall/CRC. Taylor and Tibshirani (2015) Statistical learning and selective inference. PNAS, 112 (25): 7629- 7634. Tibshirani, et al (2003) Class Prediction by Nearest Shrunken Centroids, with Applications to DNA Microarrays. Statistical Science, 18(1): 104-117. · Software Software: R is a free software environment for statistical computing and graphics, which can be downloaded at http://www.r-project.org/. METHODS FOR DETERMING FINAL GRADE The course grade will be based on three components: 1. Homework and discussion participation 70% 2. Final Project/Exam 30% Homework will be assigned on a regular basis and there are about 7 homework assignments. No credit will be given for late homework without prior consent of the instructor. The write-up of your solutions should represent your own work. Weekly participation in Discussion boards through Canvas is required. See Canvas instructions. The final project/exam is tentatively scheduled on the last week of semester. EVAULATION OF STUDENT LEARNING At the completion of this course, you will receive a letter grade reflecting your performance in this course. Letter grades (from A – F) will be computed for each of the above items based on the percentage earned. Your percentage total is then converted to a letter grade according to the following scale: Letter Grade Equivalent:Percentage Earned:Grade Point: A95-1004.00 A-90-943.67 B+87-893.33 B83-863.00 B-80-822.67 C+77-792.33 C73-762.00 C-70-721.67 D+67-691.33 D60-661.00 FBelow 600.00 INone0.00 WNone0.00 ATTENDANCE POLICY Students are responsible for all material covered in the course. Therefore, students are expected to participate in ALL course discussions and activities unless illness or an emergency occurs. No extension is permitted on the deadlines without prior permission of the instructor. Permission will be granted only in case of an emergency or illness; student must make arrangements to complete the missed deadlines. LATE WORK POLICY Assignments are due as stated unless modified by the instructor. Assignments will not be accepted late unless under extraordinary circumstances. STATEMENT ON ACADEMIC INTEGRITY Academic integrity is vital to the learning process and dishonesty will not be tolerated. Any student who commits academic dishonesty will receive a sanction appropriate to the nature and severity of the violation and in accordance with the Policy on Academic Integrity, which appears in detail in the course catalog (available under Academics on Bay Path Connect). If you are unclear as to what types of behaviors constitute academic dishonesty, talk with the course instructor. (The entire policy may be found at http://tinyurl.com/clwhq5u) A faculty member who has evidence of a student failing to adhere to the Academic Integrity Policy has a duty to report the conduct to the Office of Academic Affairs, which will maintain records of the allegation and the disposition of the matter. When conduct involving academic dishonesty occurs in the faculty member’s class, she or he may elect to attempt to resolve the matter informally, in which case the faculty member may assign the student a grade of “F” for the course and/or for the particular assignment, or grade so much of the assignment that represents the student’s own work, or require that the student repeat the assignment or a similar assignment. The faculty member may elect to refer the matter directly to Academic Affairs for disposition by the Standing Committee through a Hearing Board. PROCEDURES FOR STUDENTS WITH DISABILITIES If you have an identified disability that may affect your performance in this class and you choose to request reasonable accommodations, please schedule an appointment with the Director of Student Academic Support Services, Jemi Kuberski, at
[email protected], as soon as possible, so that provisions can be made to assure you have an equal opportunity to meet all the requirements of this course. COURSE OUTLINE Topics To Be Covered: · Week 1: Overview of classification. Review of logistic regression, logistic regression in high-dimensional setting (penalized logistic regression). Classification methods: linear discriminant analysis, quadratic discriminant analysis, K-nearest neighbors. · Week 2: Comparison of classification methods. Lab 1: classification methods. Classification in high-dimensional setting: penalized logistic regression (discussed in Week 1), nearest centroid method · Week 3: Introduction to support vector machine, maximal margin classifier, construction of maximal margin classifier. Non-separable case and Support vector classifier, support vector machines, application to the heart disease data. Lab 2: support vector machine. · Week 4: Overview of tree-based methods, regression trees, recursive binary splitting, classification trees. Lab 3: Tree based method · Week 5: Pros and cons of trees, bagging, random forests, boosting. · Week 6: Unsupervised learning: clustering, k-means, hierarchical agglomeration · Week 7: Advanced discussion on Clustering, Principal Component analysis · Week 8: Concluding remarks of the course. FEDERAL CREDIT HOUR Except as provided in 34 CFR 668.8(k) and (l), a credit hour is an amount of work represented in intended learning outcomes and verified by evidence of student achievement that is an institutionally established equivalency that reasonably approximates not less than – (1) One hour of classroom or direct faculty instruction and a minimum of two hours of out of class student work each week for approximately fifteen weeks for one semester or trimester hour of credit, or ten to twelve weeks for one quarter hour of credit, or the equivalent amount of work over a different amount of time or (2) At least an equivalent amount of work as required in paragraph (1) of this definition for other academic activities as established by the institution including laboratory work, internships, practica, studio work, and other academic work leading to the award of credit hours. TECHNOLOGY EXT 099 Introduction to Online Learning Course: All online students are required to successfully complete EXT 099: Introduction to Online Learning prior to beginning any online course at Bay Path. If you have any questions about this requirement, please contact the Center for Online Learning at
[email protected]. Computer Requirements: In order to effectively participate in and successfully complete this course, each student must meet the minimum hardware, software, and connectivity computer specifications as outlined by the Information Technology Services department at Bay Path University. The technology requirements document is available in the Student Canvas Tutorial in Canvas. Communications from the University: The University provides a free e-mail account to all of our students. Please be sure to check this e-mail account regularly by logging on to the My Bay Path portal at my.baypath.edu. Important campus messages are often sent to this email account. Be sure to check your Conversations Inbox in Canvas on a regular basis (daily is recommended) as all course-related communication (e-mail from your instructor and other students) will be sent through this module. You can see if you have new messages on your course home page when you first log in. It is also important set your "Notifications Preferences" within your Canvas profile. These notifications will alert you of activity within your Canvas classroom via the method you choose. Remember that Canvas Conversations are not the same as your Bay Path email account. Each must be checked separately. Technology-Related Issues and Problems The Bay Path University Technology Support Center (TSC) is always available to assist you with technology related issues that may arise during your courses. The best way to contact them is through the “Tech Support” link on the My Bay Path portal. You can also e-mail your questions or problems to
[email protected] or you can call the TSC at 413-565-1487. TSC hours of support services are posted on the IT Resources page of the My Bay Path portal. Be sure to be as specific as possible when requesting assistance; this will help you receive assistance more quickly. Online Learning Questions or Issues The Center for Online and Digital Learning staff is available to answer any of your questions regarding online learning and to provide you with strategies and suggestions for being an effective online learner. For assistance, please email
[email protected] or call 413-565-6880. E-MAIL & CANVAS Every student is required to use the University’s e-mail and the Canvas course management system. DISCLAIMER The professor reserves the right to change topics covered or the order in which they are covered at his/her discretion (after advance notification to the class). The students are hereby advised that select copies of their work in this class may be retained by the professor or Bay Path University for educational or administrative purposes. © 2019 by The Hartford. Classification: Non-Confidential. No part of this document may be reproduced, published or used without the permission of The Hartford. © 2019 by The Hartford. Classification: Non-Confidential. No part of this document may be reproduced, published or used without the permission of The Hartford. Page 5 © 2019 by The Hartford. Classification: Non-Confidential. No part of this document may be reproduced, published or used without the permission of The Hartford.