Lecture: 2 hours/week
and
Lab: 2 hours/week
In this course, students participate in a variety of learning activities such as lecture demonstrations, in-class exercises, in-class discussions, hands-on group or individual projects, and background research activities.
- Programming Foundations for AI Development using high-level programming languages such as Python
- AI Concepts and Large Language Models, including model architecture, pre-training, fine-tuning, generative AI application types (language modelling, question answering, code generation, content creation, logical reasoning), and LLM limitations (bias, hallucination, sustainability, output control)
- Prompt Engineering, including zero-shot, few-shot, and chain-of-thought techniques, and prompt evaluation across generative AI tasks
- Applied AI Development, including production-ready environment setup, pre-trained model deployment using Docker, GitHub, LangChain, and Hugging Face, and Retrieval-Augmented Generation (RAG) pipeline implementation
- Cybersecurity Considerations for AI, including threat identification, mitigation, robustness, and data protection
- Ethics and Responsible AI, including ethical risks, privacy, intellectual property, and compliant AI usage
- AI-augmented System Design and Development, including integration of generative models into software workflows and end-to-end application development from requirements to deployment
Upon successful completion of this course, the student will be able to:
- Apply programming fundamentals in a high-level language such as Python to develop AI-powered programs and solutions.
- Analyze the architecture, pre-training, fine-tuning, application types, and limitations of Large Language Models (LLMs) including bias, hallucination, and challenges in controlling model output.
- Evaluate prompting strategies including zero-shot, few-shot, and chain-of-thought techniques across varied generative AI tasks.
- Implement a Retrieval-Augmented Generation (RAG) pipeline within a production-ready development environment using tools such as Docker, GitHub, LangChain, and Hugging Face.
- Assess cybersecurity threats, ethical risks, privacy concerns, and intellectual property implications in generative AI systems using industry standards and responsible AI principles.
- Design an AI-augmented application that integrates a generative model into a functional software workflow from requirements to deployment.
This is a letter-graded course. Assessment will be based on course objectives and will be in accordance with the Douglas College Evaluation Policy.
|
Labs/Assignments |
10-15% |
|
Project w/ Presentation* |
20-25% |
|
Midterm Examination** |
30-35% |
|
Final Examination** |
30-35% |
|
Total |
100% |
Dhamani, N., & Engler, M. Introduction to generative AI. Manning Publications. Latest Edition
Rodriguez, C. Generative AI foundations in Python: Discover key techniques and navigate modern challenges in LLMs. Packt Publishing. Latest Edition
OR
Other textbook approved by the department.
Minimum Grade C in CSIS 1175
None
None