Skip to content

CSC 461: Machine Learning (Fall 2024)

This syllabus is subject to change at the instructor's discretion. Any modifications will be communicated to students with reasonable notice.

Course Description

Machine Learning is a rapidly evolving subdiscipline of Artificial Intelligence and Computer Science that focuses on the development and study of algorithms that can learn from and make predictions or decisions based on data. This course offers a comprehensive introduction to the theoretical foundations and practical applications of machine learning algorithms. Students will investigate how machine learning and neural networks power state-of-the-art systems in natural language processing, computer vision, and reinforcement learning applications. The course covers a wide range of topics, including supervised and unsupervised learning, neural networks, and best practices in applying machine learning to real-world problems. By the end of the course, students will have developed a strong understanding of machine learning principles and the ability to implement and evaluate machine learning models using modern tools and frameworks.

Prerequisites: CSC 310 and MTH 215.

Course Information

  • Instructor:
  • Lectures:
    • MWF 2-2:50p

  • Teaching Assistants:

    • Office Hours: All office hours will be held in the Computer Science Department's lounge on the top floor of Tyler Hall. Office hours will be held in person, but students may also attend virtually via Zoom.

    • Calvin Higgins: M 12-2p

    • Jacob Dauphinais: M 4-6p
    • Jacob Dauphinais: T 11-1p
    • Maedeh Hosseinpour: W 12-2p
    • Calvin Higgins: Th 12:30-2:30p
    • Maedeh Hosseinpour: F 12-2p

Support Tools and Technologies

Students in this course will utilize the following platforms for communication, assignments, and assessment. All students are required to use their primary email from eCampus for accessing these platforms. Automatic registration will be provided for students.

Placeholder Ed Discussion: Serves as the primary platform for academic discussions, polls, and quizzes. Ed facilitates student engagement with peers and instructors, fostering knowledge sharing and comprehension of key concepts. The platform's intuitive interface supports various discussion formats, including text, code snippets, and mathematical equations, making it ideal for machine learning topics [Ed Help].

Placeholder Gradescope: Streamlines the assignment submission and grading processes, ensuring prompt and consistent feedback from instructors. Gradescope's advanced features allow for efficient grading of written and programming assignments. Students can review their evaluated work, analyze detailed feedback, and identify areas for improvement. The platform also supports regrade requests, promoting transparency in the assessment process [Gradescope Help Center].

Placeholder Zoom: Facilitates virtual office hours, providing a flexible means for students to interact with instructors and teaching assistants. Zoom's screen sharing and whiteboard features enable effective remote collaboration especially on coding problems. Students can participate in one-on-one or group sessions, enhancing their understanding of course material through direct engagement with instructors [Zoom Support].

The integration of these technologies aims to create a comprehensive and interactive learning environment, supporting the diverse aspects of machine learning, from theoretical discussions to practical implementations.

Assessment and Grading

  • Homework Assignments (15%)
  • Midterm Exam (30%)
  • Final Exam (30%)
  • Final Project (25%)

Final letter grades are assigned according to the following scale. The final letter grade corresponds to the highest threshold value less than or equal to the student's final numerical grade.

A    A-    B+    B    B-    C+    C    C-    D+    D    F
94   90    87    83   80    77    73   70    67    60   0

Homework Assignments

Homework assignments are to be completed individually unless explicitly stated otherwise in the assignment instructions. Students will typically have 6-9 days to complete each assignment, with specific due dates clearly indicated on the course website.

Late submissions will NOT be accepted. To maximize learning outcomes and receive valuable feedback, students are strongly encouraged to discuss their code, solutions, or questions during the instructor/TA's office hours prior to assignment due dates.

Examinations

The course includes midterm and final examinations, both conducted in-person. These exams assess students' understanding of machine learning concepts and problem-solving skills. Key points:

  • exams are individual and open-book (printed materials only);
  • no electronic devices are allowed during exams;
  • make-up exams are granted only for exceptional, documented circumstances and must be approved by the instructor.

Final Project

The Final Project is a key component of this course, allowing students to apply machine learning concepts to real-world problems. Working in groups, students will either select a project from a provided list or propose their own, subject to instructor approval. Each project involves implementing and evaluating a sophisticated machine learning solution, with deliverables including a progress report, final report, and live presentation. At the semester's end, groups will showcase their work in a dedicated ML Workshop, providing an opportunity to demonstrate their achievements to peers and instructors. To encourage exceptional effort and innovation, outstanding projects may be awarded significant extra credit, recognizing the application of course concepts to practical, impactful solutions.

Academic Integrity

This course encourages collaborative discussions and peer learning to enhance understanding of course topics. However, students must maintain the highest standards of academic integrity in all their work. For written assignments and programming projects, sharing solutions, copying another student's work, or using uncredited AI-generated content is strictly prohibited. These actions constitute plagiarism, a serious academic offense that carries significant consequences as outlined in the University's Academic Honesty Procedures.

AI and Large Language Models (LLMs)

This course embraces the integration of AI tools such as ChatGPT, Gemini, Claude, or Github Copilot as learning aids. Students are encouraged to leverage these technologies for brainstorming, concept exploration, code analysis, and problem-solving approaches. These tools can enhance understanding of computer organization concepts and aid in various aspects of coursework. However, it is crucial to maintain a balance between AI assistance and learning. While AI can enhance learning, it should complement rather than replace students' critical thinking and problem-solving skills. The primary goal remains the development of individual competence in machine learning concepts and applications.

All student submissions that incorporate AI-generated content must include proper citation. This includes, but is not limited to, assignments, presentations, and any other coursework where AI tools have been used to generate, edit, or enhance the content. Students must clearly indicate which portions of their work were created with AI assistance and specify the AI tool used.

Students should view AI-generated content as a starting point, building upon it with their own understanding and critical analysis. For programming assignments, a thorough comprehension of any AI-suggested code is essential before incorporation. Students are encouraged to seek instructor guidance if uncertain about appropriate AI tool usage.

It's crucial to verify AI-generated information, as these tools can produce errors or outdated content.

Disability Accommodations

Students with documented disabilities are encouraged to contact the instructor as early in the semester as possible to arrange appropriate accommodations. As part of this process, students should first contact the Disability Services for Students Office, located in room 302 of the Memorial Union (401-874-2098).

Religious Observances

In accordance with University of Rhode Island policy, students are granted the opportunity to observe their traditional religious holidays. Students wishing to observe a holiday of special importance must provide written notification to the instructor in advance.