Syllabus

General Course Information

Catalog ID: ISYE 4600
Credit Hours: 3
Schedule: — Location: —

Instructor & TA

Instructor: Mohsen Moghaddam
Email: mohsen.moghaddam@gatech.edu
Office Hours & Location: —

Teaching Assistant: —
TA Email: —
TA Hours & Location: —

Description

Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed. This course addresses fundamental questions in machine learning: What are the most important methods to know, and why? How can we compare methods for a specific dataset? How can we evaluate errors on future data? What’s the “right” objective function? How do we tune parameters?

The course provides senior undergraduate students with grounding in the methods, theory, mathematics, and algorithms of machine learning, enabling them to understand and apply machine learning techniques to real-world problems.

Prerequisites

  • Undergraduate-level probability, linear algebra, and statistics
  • Basic programming using Python (or equivalent)

Learning Outcomes

By the end of the semester, students will be able to:

  • Identify, formulate, and solve engineering problems using engineering, science, and mathematics
  • Produce solutions considering public health, safety, and societal contexts
  • Communicate effectively with diverse audiences
  • Recognize ethical and professional responsibilities
  • Work effectively in teams with leadership and collaboration
  • Develop and conduct experiments, analyze and interpret data
  • Acquire and apply new knowledge using appropriate strategies

Course Requirements & Grading

Grading Components

  • Homework (50%)
  • Quizzes (20%)
  • Project (30%):
    • Project Proposal: 5%
    • Project Report: 20%
    • Peer Evaluation: 5%

Grading Scale

A: 90–100%
B: 80–89%
C: 70–79%
D: 60–69%
F: Below 60%

Course Materials

Content

  • Course material will be provided in lecture slides.
  • Bishop, C. M. Pattern Recognition and Machine Learning
  • Hastie, T., Tibshirani, R., & Friedman, J. The Elements of Statistical Learning (2nd Ed)
  • Murphy, K. P. Probabilistic Machine Learning: An Introduction

Communication

  • Canvas: Check daily for announcements and updates
  • TA Communication: Email TA for grading or administrative requests
  • Course Questions: Use Ed Discussion for course-related questions

Policies, Expectations, & Guidelines

Homework Policies

  • Submit via Canvas by 11:59 PM EST
  • Multiple submissions allowed before deadline (last counts)
  • Must include explanations and conclusions (not raw output)
  • Python (3.x) required; Colab environment provided
  • Code must be self-contained and executable

Late Policy

  • Up to 10 total extension days (max 7 per assignment) without penalty
  • After extensions are used:
    • 1 day late: 75% credit
    • 2 days late: 50% credit
    • 3 days late: 25% credit

    • 3 days late: no credit

Project

  • Teams of up to 3 students (self-formed)
  • Real-world machine learning problem required
  • Must include data-driven analysis
  • Deliverables:
    • Proposal (mid-semester)
    • Final Report
    • Peer Evaluation

Academic Integrity

Students must follow the Georgia Tech Honor Code. All work must be original. Violations will be reported to the Office of Student Integrity.

Accommodations

Students requiring accommodations should contact the Office of Disability Services and notify the instructor.

AI Policy

AI tools (e.g., ChatGPT, coding assistants) may be used as learning aids. However:

  • Do not copy AI-generated content into assignments
  • Work must reflect your own understanding
  • Be able to explain all submitted work

Guidelines:

  • Use AI to study concepts and explore explanations
  • Avoid using AI during assignment completion
  • Ensure independent work

Course Schedule

(Due dates for homework and project deliverables will be provided via Canvas.)

  • Week 1: Introduction
  • Week 2: Clustering
  • Week 3: Principal Component Analysis (Project Team Formation)
  • Week 4: Recommender Systems (Homework 1)
  • Week 5: Feature Selection
  • Week 6: Bias–Variance Tradeoff & Cross Validation (Project Proposal)
  • Week 7: Basic Optimization
  • Week 8: Classification (Homework 2)
  • Week 9: Support Vector Machines
  • Week 10: Neural Networks
  • Week 11: Anomaly Detection (Homework 3)
  • Week 12: Boosting Algorithms
  • Week 13: Decision Trees & Random Forests
  • Week 14: Large Language Models (Homework 4)
  • Week 15: Final Project Presentations (Final Report Due)