705.623.81 - AI Algorithm Design and Analysis
Description
This course provides an in-depth exploration of the design, analysis, and optimization of algorithms critical to artificial intelligence. Building on foundational algorithmic techniques such as dynamic programming, graph theory, and heuristic search, the course extends into applications across machine learning, natural language processing, computer vision, and generative AI. Topics include computational complexity, probabilistic reasoning, optimization methods, and trade-offs in algorithm performance. Students will gain theoretical and practical insights essential for solving real-world AI problems, including designing hybrid AI systems that integrate reasoning, optimization, and pattern recognition.
Instructors
Course Structure
The course materials are divided into 14 modules which can be accessed by clicking Modules on the course menu. A module will have several sections including the overview, content, readings, discussions, and assignments. You are encouraged to preview all sections of the module before starting. The modules run for a period of seven (7) days, from Tuesdays to the following Mondays. Exceptions, if any, are noted in the Course Schedule below. You should regularly check the Calendar and Announcements for any updates on assignment due dates and/or schedule changes. If you are taking the course in the Summer, please note that Modules 1 and 2 are combined as well as Modules 13 and 14 to ensure all 14 modules are covered during the 12 weeks for the Summer semester.
Course Topics
- Introduction to AI Algorithms and Computational Complexity
- Graph Algorithms for AI Applications
- Dynamic Programming and Optimization Methods
- Heuristic Search and Adversarial Search
- Probabilistic Algorithms and Bayesian Networks
- AI Planning and Constraint Solving
- Linear Algebra and Matrix Algorithms for Machine Learning
- Gradient-Based Optimization and Learning Algorithms
- Markov Decision Processes and Reinforcement Learning Foundations
- Genetic Algorithms and Evolutionary Computation
- Generative Algorithms
- Graph Neural Networks and Transformer-Based Models
- Hybrid AI: Combining Symbolic and Connectionist Approaches
- Responsible AI and the Road Ahead
Course Goals
The course AI Algorithms Design and Analysis is designed to equip students with the theoretical foundations and practical skills needed to develop, analyze, and optimize algorithms central to modern AI systems. It covers core techniques such as graph algorithms, dynamic programming, probabilistic reasoning, machine learning, generative models, and hybrid AI, with a strong emphasis on real-world applications and ethical considerations.
Course Learning Outcomes (CLOs)
- Analyze and evaluate algorithmic efficiency using computational complexity theory, trade-offs in performance, and optimization techniques.
- Design and implement search and optimization algorithms (e.g., heuristic search, dynamic programming, and graph-based methods) for AI applications.
- Apply probabilistic reasoning and decision-making models, including Bayesian networks and Markov models, to AI problems.
- Develop and optimize machine learning algorithms through mathematical foundations such as linear algebra, gradient-based optimization, and reinforcement learning.
- Implement generative AI techniques, including autoencoders, GANs, and transformers, to create AI-driven generative models.
- Integrate hybrid AI techniques that combine symbolic and neural-based approaches for complex problem-solving.
- Critically assess AI algorithms for ethical considerations, including fairness, accountability, and bias mitigation.
Textbooks
- Thomas H. Cormen, Charles E. Leiserson, Ronal L. Rivest and Clifford Stein, Introduction to Algorithms, 4th Edition, MIT Press, 2022. https://mitpress.mit.edu/9780262046305/introduction-to-algorithms/ (Available online in JHU Library Catalyst)
- Stuart J. Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 4th Edition, Prentice Hall, 2020. https://aima.cs.berkeley.edu/
- Christopher M. Bishop and Hugh Bishop, Deep Learning: Foundations and Concepts, Springer, 2024. https://www.bishopbook.com/
- Ian Goodfellow, Yoshia Bengio and Aaron Courville, Deep Learning, MIT Press, 2016. https://www.deeplearningbook.org/
- Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. https://www.microsoft.com/en-us/research/publication/pattern-recognition-machine-learning/
Required Software
- Python: Students must have access to a recent version of Python
- Jupyter Notebook: Course assignments will be completed using Jupyter Notebook files
- Integrated Development Environment (IDE)
- Students will need an IDE to run your Python code and Jupyter Notebooks
- We highly recommend using Visual Studio Code (with the Jupyter extension), but students may use any IDE or setup they prefer.
Student Coursework Requirements
- Module Activities (20%): Module activities are built into each module and are intended to be completed as you work through the learning materials.
- Module Review Quizzes (20%): Weekly sets of review questions to reinforce key module concepts.
- Formative Assignments (60%)
- Cover 2–3 modules at a time with varied formats.
- Emphasize coding, algorithm analysis, and problem-solving.
- Evaluate both theoretical understanding and practical implementation.
Grading Policy
EP uses a +/- grading system (see "Grading System", Graduate Programs catalog, p. 10).
| Score Range | Letter Grade |
|---|---|
| 100-97 | = A+ |
| 96-93 | = A |
| 92-90 | = A− |
| 89-87 | = B+ |
| 86-83 | = B |
| 82-80 | = B− |
| 79-77 | = C+ |
| 76-73 | = C |
| 72-70 | = C− |
| 69-67 | = D+ |
| 66-63 | = D |
| <63 | = F |
Course Policies
Attendance Policy
- Attendance is not required for this course. However, students are responsible for regularly reviewing Canvas Announcements and the course Calendar for updates or changes as the course progresses.
- Students must properly cite all external sources used in assignments, including textbooks, academic papers, websites, datasets, code repositories, and Generative AI tools, when applicable.
- Citations should clearly indicate what source was used and how it informed your work.
- Failure to provide appropriate citations may be considered a violation of academic integrity.
- Citations identifying the specific AI model(s) or website(s) used
- A brief written description of how Generative AI was used
- Treat Generative AI as a learning aid, not an authority.
- Verify all AI outputs, as they may contain errors, bias, or incorrect assumptions.
- Apply academic skepticism to all online information, including AI-generated content. Confidence does not imply correctness.
- Students are expected to submit all assignments by the posted deadlines.
- If you anticipate a late submission, you must communicate with the instructors in advance (via email or Microsoft Teams).
- When prior communication is provided, late penalties may be waived at the instructor’s discretion.
- If no prior communication is received, a late penalty of 5 points per day will be applied according to course grading standards.
- In exceptional circumstances, students should notify the instructors as soon as possible.
Academic Policies
Deadlines for Adding, Dropping, and Withdrawing from Courses
Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar. Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.
Academic Misconduct Policy
Students with Disabilities - Accommodations and Accessibility
Student Conduct Code
Classroom Climate
JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity. If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).
Course Auditing
When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team (EP-Registration@exchange.johnshopkins.edu) in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.