Module 3 - Machine Learning, Model Training & Prompt Engineering

Understanding the foundations behind how a generative AI model is built and used effectively is an asset. In this course, we take it a step further by exploring the basics of machine learning in detail so you understand how some systems that predict commerce, treat our water, and personalize media are developed and function.

Understand types of data and machine learning methods.
Apply a machine learning methodology.
Explore ethical considerations in data collection and usage.
Prompt with zero-shot, one-shot, few-shot and CIC prompting techniques.

From Understanding Machine Learning to Deploying It

This is Module 3 of CAIAI’s Introduction to Artificial Intelligence course, available as an individual module, and it goes into concepts such as the types of machine learning, the importance of data selection and preprocessing, the ethics attached to data use, a Machine Learning Methodology you can apply to plan and deploy a project, and prompt engineering to optimize generative AI outputs.

Course at a Glance

Format: Online and self-paced (asynchronous), through the CAIAI learning platform.
Duration: 7.25 hours across three chapters, plus a module assignment.
Level: Beginner.
Who it is for: Post-secondary students, independent adopters such as businesspeople and entrepreneurs, and large-scale industry adopters reskilling and upskilling.
What you receive: A digital credential on completion, the relevant chapters of the Introduction to Artificial Intelligence textbook, course videos and discussion boards, with six months of access from the date of purchase.
Cost: $450.00 CDN.
Next start date: Enrolment is open, and the module is self-paced, with no fixed cohort dates.

What Is the Machine Learning Module?

The module runs across three chapters:

Chapters 6 and 7 cover machine learning fundamentals, data, and training. They explore concepts such as supervised, unsupervised, semi-supervised, and reinforcement learning methods, the types of data behind them, and why preprocessing often determines model performance more than most people expect.
Chapter 8 covers prompt engineering and mitigating hallucinations and artifacts in AI outputs.

Pairing machine learning with prompt engineering in one module is deliberate, as prompting is the communication interface most people have to a trained model, and it makes considerably more sense once you know what the model was trained on and where its confidence comes from. The specific ground includes machine learning, data selection, ML implementation, model training, AI ethics, prompt engineering and AI hallucination mitigation.

The materials consist of chapter readings from the Introduction to Artificial Intelligence textbook, course videos, and online discussions where you post at least one comment addressing each chapter’s prompt. Chapters 6 and 8 close with a quiz requiring 70% or higher; chapter 7 is assessed through discussion and the module assignment. Nothing is delivered live, so you won’t miss any sessions.

What You Will Learn

Differentiate between the various types of data and machine learning methods, such as supervised, unsupervised, semi-supervised, and reinforcement learning, and understand their applications in AI.
Understand the relationship between data quality, preprocessing, and model performance in machine learning.
Evaluate the ethical considerations in data collection and usage, including privacy, consent, and bias mitigation.
Implement the Machine Learning Methodology to plan, develop, and deploy machine learning projects.
Identify and mitigate common issues in generative AI outputs, such as hallucinations and artifacts.
Apply prompt engineering techniques, including zero-shot, one-shot, and few-shot prompting, as well as the CIC method, to achieve desired generative AI outputs.
Assess prompt effectiveness and refine it through continuous feedback and adjustments.

What Is Included

Textbook chapters: Chapters 6, 7 and 8 of the Introduction to Artificial Intelligence textbook.
Course videos: Video teaching alongside each chapter reading, including three-quarters of an hour on prompt engineering.
Group discussion boards: A prompt for each of the three chapters, and everyone else’s answers to read.
Chapter quizzes and a module assignment: Two quizzes at 70% to pass, plus an assignment applying the methodology.
Digital credential: Awarded on completion of the module.
Course access: Six months of access from the date of purchase.

Why Machine Learning Skills Matter Now

Most cannot yet. The Future Skills Centre found that only 31% of small and medium-sized organizations could clearly articulate the specific AI skills they needed, while demand for core AI skills rose 37% between 2018 and 2023 and workers with AI competencies command a 56% wage premium.

Statistics Canada found that among businesses with 100 or more employees using AI, 32.8% hired employees with AI-related skills and 30.2% used external consultants or vendors. Both routes need someone inside the organization who can specify the work and judge whether it was done.

Being able to understand which ML method could potentially solve a problem and what data it could need is a different contribution from simply looking up terms in a vendor deck.

Who We Have Taught, and What Changed for Them

We have taught this material to people who will never train a model themselves: property maintenance and land management teams, chamber of commerce members, executives across manufacturing, agriculture and professional services, and university faculty and students. Below are just a few of those engagements:

Greyspace Maintenance: Business audits, an adoption framework and four workshops leading to generative AI in daily operations.
Abbotsford Executive Association: An introductory session for Fraser Valley executives across manufacturing, agriculture, technology and professional services.
University of the Fraser Valley: Three workshops reaching close to 100 staff, faculty, students and alumni.
ZVS Land Management: Training and consulting later featured in our textbook’s prompt engineering chapters.

Ways to Cover the Cost

Learners or employers are usually unaware of opportunities to pay for their learning. We have shared resources to help you identify available funding opportunities, including scholarships for individuals and grant programs for individuals and employers.

Canadian AI Education Scholarships: Our own stream, open to anyone seeking AI literacy, offering 30% off tuition.
Higher-Ed AI Education Scholarships: A tuition discount for college and university students, available through our institutional partnerships.
Government and Industry Workforce Training Grants: Available funding opportunities for teams and individuals supported by government, public and private sector organizations.

Apply for a scholarship through our Canadian AI scholarships page. In addition, visit our Canadian AI grant funding page to see what individuals or employers can apply for.

Where This Module Fits

Introduction to Artificial Intelligence: The full course this module belongs to, and the better value if you intend to take more than two modules.
AI Certification: The Canadian AI Professional credential, which the full course awards and individual modules do not.
AI Courses for Beginners: The wider catalogue, including shorter and lower-cost beginner courses on machine learning and on prompting.
Corporate AI Education and Training: The route if your employer wants a team able to specify and assess machine learning work.

Enrol in This Module

You can enrol directly on our learning platform, or use the form below if you want to ask any additional questions.

Our Mission

Our mission is to help Canadians learn, adapt and succeed with AI. Machine learning is where most people decide the subject is not for them. It is, and this module is built to prove it by having you plan a real project rather than memorise a taxonomy.

Table of Contents