Southern Utah University

Course Syllabus

Back to Syllabus Search | Browse by Department
Southern Utah University
Southern Utah University
Fall Semester 2025

Advanced Data Analytics (Online)

ANLY 6500-B70

Course: ANLY 6500-B70
Credits: 3
Term: Fall Semester 2025
Department: MESA
CRN: 30156

Course Description

This course provides an overview of advanced machine learning, data mining and data analytics applications. The main topics of the course can be organized as follows: Anomaly and Outlier Detection, Categorical and Regression Trees (CART), Time-series, K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Gradient Boosting (GB), Random Forests (RF), Cluster Analysis, Support Vector Machines (SVM). (Fall - 2nd Session) [Graded (Standard Letter)] Prerequisite(s): ANLY 6110 Prerequisite Min Grade: C Registration Restriction(s): Masters of Science in Business Analytics

Required Texts

Please note: our course lectures will be the main course resources. The materials listed below are optional, but incredibly helpful for understanding data analytics concepts.

  • Dive into Deep Learning, by Aston Zhang (Author), Zachary C. Lipton (Author), Mu Li (Author), Alexander J. Smola (Author), Publisher: Cambridge University Press, Publication date: December 7, 2023, Edition: 1st, Language: English, ISBN-10: 1009389432, ISBN-13: 978-1009389433

    1. Textbook Link: https://d2l.ai/ 
  • Automate the Boring Stuff with Python, 2nd Edition: Practical Programming for Total Beginners, Author: Al Sweigart, Publisher: No Starch Press; 2nd edition (November 12, 2019), ISBN-10: 1593279922, ISBN-13: 978-1593279929,
       O'Reilly Online Textbook:

  1. SUU Login Link: https://go.oreilly.com/southern-utah-university?state=/home/
  2. Textbook Link: https://learning.oreilly.com/library/view/automate-the-boring/9781098122584/xhtml/ch01.xhtml#ch01lev1sec1 
    A free online edition of the textbook https://automatetheboringstuff.com/ is available under a Creative Commons license

Learning Outcomes

Upon successful completion of this course, students will be able to:

1. Demonstrate Proficiency in Python for Deep Learning Applications

  • Apply core Python programming constructs, including data structures, loops, functions, and classes, to support deep learning workflows.

  • Implement object-oriented principles such as constructors and callable functions for model and data pipeline design.

2. Explain Core Concepts of Deep Learning and Model Architectures

  • Articulate the foundational principles behind neural networks and deep learning.

  • Describe the structure and training processes of regression and classification models using neural networks.

3. Build and Train Deep Learning Models Using PyTorch

  • Utilize PyTorch to construct and train models for supervised learning tasks.

  • Apply appropriate loss functions (MSE, Cross-Entropy, BCE) based on problem context.

  • Use and compare various activation functions, including custom implementations.

4. Prepare and Manage Datasets for Machine Learning Workflows

  • Load and preprocess built-in and custom datasets using PyTorch Dataset and DataLoader modules.

  • Implement data transformation techniques such as normalization, resizing, and augmentations for training robustness.

5. Integrate Learning Rate Schedulers into Training Pipelines

  • Justify the use of different learning rate schedulers and integrate them into model training loops.

  • Evaluate and select suitable schedulers (e.g., StepLR, CosineAnnealingLR) for specific training scenarios.

6. Apply Transfer Learning for Efficient Model Development

  • Adapt pretrained models (e.g., ResNet) for new tasks by modifying output layers and freezing intermediate layers.

  • Evaluate the performance gains from transfer learning and select appropriate pretrained models.

7. Implement NLP Tasks Using Large Language Models and Transformers

  • Use the Hugging Face Transformers library to perform NLP tasks such as sentiment analysis, NER, question answering, summarization, and text generation.

  • Fine-tune state-of-the-art pretrained LLMs for custom applications.

8. Develop and Evaluate End-to-End Deep Learning Applications

  • Design and deploy practical applications such as a basic ChatGPT-style app using Python and PyTorch.

  • Critically evaluate model performance, optimize hyperparameters, and refine models through iterative testing.

These outcomes ensure that students will leave the course with practical, in-demand skills for careers in data analysis, management information systems, and other data-centric fields.

Course Requirements

Participation in this course will require basic technology  for all online classes at Southern Utah University:

  • A computer with reliable Internet access
  • A web browser (The browser requirements page identifies which browsers are supported and other technical information for operating Canvas.)
  • Acrobat Reader
  • Microsoft Word or another word processor, such as Open Office
Additional technologies  required for this course include: 

Course Outline

Homework Assignments

You will complete specific Python data analytics coding tasks related to the course module content.


Instructor's policies on late assignments and/or makeup work

  • All assignments will be closed for submission at 5:00 PM on December 5, 2025 (Mountain Time - Denver, GMT-06:00). Students' submissions should be made before 5:00 PM on December 5, 2025 (Mountain Time - Denver, GMT-06:00).
  • Assignments submitted after the due date will incur a penalty based on the total points possible for the assignment, not the points earned. Assignments submitted after the due date will incur a penalty of 10% per 24-hour period. The penalties are applied as follows:
    • Within 24 hours of the due time: A 10% deduction from the total points will be applied.
      Example: If the total points for an assignment are 10 and a student's grade without penalty is 8 points, the 10% deduction will result in a 1-point deduction, not 0.8 points.

    • 24 to 48 hours past the due time: A 20% deduction from the total points will be applied.
      Example: For an assignment worth 10 points, this will result in a 2-point deduction.

    • 48 to 72 hours past the due time: A 30% deduction from the total points will be applied.
      Example: For an assignment worth 10 points, this will result in a 3-point deduction.

    • 72 to 96 hours past the due time: A 40% deduction from the total points will be applied.
      Example: For an assignment worth 10 points, this will result in a 4-point deduction.

    • ...

    • 192 to 216 hours past the due time: A 90% deduction from the total points will be applied.
      Example: For an assignment worth 10 points, this will result in a 9-point deduction.

    • 216 or more hours past the due time: a grade of zero will be recorded.

  • If there are extenuating circumstances, you will need to discuss those with me as soon as possible.

Attendance Policy

N.A.

Course Fees

N.A.

ADA Statement

Students with medical, psychological, learning, or other disabilities desiring academic adjustments, accommodations, or auxiliary aids will need to contact the Disability Resource Center, located in Room 206F of the Sharwan Smith Center or by phone at (435) 865-8042. The Disability Resource Center determines eligibility for and authorizes the provision of services.

If your instructor requires attendance, you may need to seek an ADA accommodation to request an exception to this attendance policy. Please contact the Disability Resource Center to determine what, if any, ADA accommodations are reasonable and appropriate.

Academic Credit

According to the federal definition of a Carnegie credit hour: A credit hour of work is the equivalent of approximately 60 minutes of class time or independent study work. A minimum of 45 hours of work by each student is required for each unit of credit. Credit is earned only when course requirements are met. One (1) credit hour is equivalent to 15 contact hours of lecture, discussion, testing, evaluation, or seminar, as well as 30 hours of student homework. An equivalent amount of work is expected for laboratory work, internships, practica, studio, and other academic work leading to the awarding of credit hours. Credit granted for individual courses, labs, or studio classes ranges from 0.5 to 15 credit hours per semester.

Academic Freedom

SUU is operated for the common good of the greater community it serves. The common good depends upon the free search for truth and its free exposition. Academic Freedom is the right of faculty to study, discuss, investigate, teach, and publish. Academic Freedom is essential to these purposes and applies to both teaching and research.

Academic Freedom in the realm of teaching is fundamental for the protection of the rights of the faculty member and of you, the student, with respect to the free pursuit of learning and discovery. Faculty members possess the right to full freedom in the classroom in discussing their subjects. They may present any controversial material relevant to their courses and their intended learning outcomes, but they shall take care not to introduce into their teaching controversial materials which have no relation to the subject being taught or the intended learning outcomes for the course.

As such, students enrolled in any course at SUU may encounter topics, perspectives, and ideas that are unfamiliar or controversial, with the educational intent of providing a meaningful learning environment that fosters your growth and development. These parameters related to Academic Freedom are included in SUU Policy 6.6.

Academic Misconduct

Scholastic honesty is expected of all students. Dishonesty will not be tolerated and will be prosecuted to the fullest extent (see SUU Policy 6.33). You are expected to have read and understood the current SUU student conduct code (SUU Policy 11.2) regarding student responsibilities and rights, the intellectual property policy (SUU Policy 5.52), information about procedures, and what constitutes acceptable behavior.

Please Note: The use of websites or services that sell essays is a violation of these policies; likewise, the use of websites or services that provide answers to assignments, quizzes, or tests is also a violation of these policies. Regarding the use of Generative Artificial Intelligence (AI), you should check with your individual course instructor.

Emergency Management Statement

In case of an emergency, the University's Emergency Notification System (ENS) will be activated. Students are encouraged to maintain updated contact information using the link on the homepage of the mySUU portal. In addition, students are encouraged to familiarize themselves with the Emergency Response Protocols posted in each classroom. Detailed information about the University's emergency management plan can be found at https://www.suu.edu/emergency.

HEOA Compliance Statement

For a full set of Higher Education Opportunity Act (HEOA) compliance statements, please visit https://www.suu.edu/heoa. The sharing of copyrighted material through peer-to-peer (P2P) file sharing, except as provided under U.S. copyright law, is prohibited by law; additional information can be found at https://my.suu.edu/help/article/1096/heoa-compliance-plan.

You are also expected to comply with policies regarding intellectual property (SUU Policy 5.52) and copyright (SUU Policy 5.54).

Mandatory Reporting

University policy (SUU Policy 5.60) requires instructors to report disclosures received from students that indicate they have been subjected to sexual misconduct/harassment. The University defines sexual harassment consistent with Federal Regulations (34 C.F.R. Part 106, Subpart D) to include quid pro quo, hostile environment harassment, sexual assault, dating violence, domestic violence, and stalking. When students communicate this information to an instructor in-person, by email, or within writing assignments, the instructor will report that to the Title IX Coordinator to ensure students receive support from the Title IX Office. A reporting form is available at https://cm.maxient.com/reportingform.php?SouthernUtahUniv

Non-Discrimination Statement

SUU is committed to fostering an inclusive community of lifelong learners and believes our university's encompassing of different views, beliefs, and identities makes us stronger, more innovative, and better prepared for the global society.

SUU does not discriminate on the basis of race, religion, color, national origin, citizenship, sex (including sex discrimination and sexual harassment), sexual orientation, gender identity, age, ancestry, disability status, pregnancy, pregnancy-related conditions, genetic information, military status, veteran status, or other bases protected by applicable law in employment, treatment, admission, access to educational programs and activities, or other University benefits or services.

SUU strives to cultivate a campus environment that encourages freedom of expression from diverse viewpoints. We encourage all to dialogue within a spirit of respect, civility, and decency.

For additional information on non-discrimination, please see SUU Policy 5.27 and/or visit https://www.suu.edu/nondiscrimination.

Pregnancy

Students who are or become pregnant during this course may receive reasonable modifications to facilitate continued access and participation in the course. Pregnancy and related conditions are broadly defined to include pregnancy, childbirth, termination of pregnancy, lactation, related medical conditions, and recovery. To obtain reasonable modifications, please make a request to title9@suu.edu. To learn more visit: https://www.suu.edu/titleix/pregnancy.html.

Disclaimer Statement

Information contained in this syllabus, other than the grading, late assignments, makeup work, and attendance policies, may be subject to change with advance notice, as deemed appropriate by the instructor.