Carleton AI Society Workshops
Workshop curriculum
Every workshop series the club has run, in the order to take it, with the slides, code and recordings that are online. Start at the top of this term's series; the earlier ones still hold up.
- Series
- 7
- Workshops
- 36
- With materials online
- 18
This term · Fall 2026
AI foundations
From how the AI you use every day actually works, through machine learning, to deep learning. No prerequisites: each workshop builds on the one before, and all years are welcome.
Intro to AI
What AI is and is not, the kinds of systems behind the tools you already use, and the map for the rest of the series.
Intro to Agentic AI
Agents: models that plan, call tools and carry a task through, and what that means for how you build with them.
Intro to Reinforcement Learning
Agents that learn by trial and error: rewards, policies, and how a system gets better from its own mistakes.
Intro to Machine Learning
Teaching a model a rule from data instead of writing the rule yourself: training, testing, and the metrics that tell you whether it worked.
Coming up · · CS Seminar Room, Herzberg 5345
Intro to Deep Learning
Neural networks: how layers of simple units learn from images and text, and training your first one.
Since 2020
Earlier series
Each series stands on its own, and the notebooks and recordings still work. Pick the one that matches where you are.
2026Hackathon workshops2 sessions · 1 with materials online
Workshops the club ran at Ottawa hackathons, for teams with a weekend to build something: using agentic AI to design and build neural networks at cuHacking 2026, and a practical introduction to machine learning at Hack the Hill III.
cuHacking Workshop – How to Use Agentic AI to Build Neural Networks
A cuHacking workshop on using agentic AI to design and build neural networks.
Machine Learning Workshop at Hack the Hill III
A practical introduction to machine learning at Hack the Hill III, a hackathon in Ottawa: the core ideas behind models, and how to bring ML into a hackathon project. The demos set a hand-written rule against a model that learns its own, then train a small PyTorch neural network on a heart-failure clinical dataset.
Winter 2026Building with AI5 sessions · 2 with materials online
Five sessions from first principles to working code: what today's models are, how to work with them, and two hands-on builds with the code to take home.
Workshop #1 – Introduction to Artificial Intelligence
An introductory workshop covering core AI concepts and real-world applications.
Workshop #2 – Vibe Coding vs Prompt Engineering
A workshop comparing vibe coding and prompt engineering in modern AI development.
Workshop #3 – What Are Large Language Models?
An introduction to large language models and how they power modern AI systems.
Building an AI Chatbot!
Learn how AI chatbots work using RAG and semantic search in LLM applications.
Training an AI Model!
Train your first machine learning model using Python in a hands-on session.
Winter 2025AI in practice3 sessions
The fundamentals, a neural network built by hand, and AI APIs in a real project.
Introduction to Artificial Intelligence
Learn the fundamentals of AI: its history, the main types of algorithms, and how to keep learning.
Build Your Own Neural Network
Beginner workshop on implementing neural networks and a demo on how to build your own model.
Using AI APIs
Learn how to use AI APIs to implement AI in your projects.
Winter 2023Language and attention2 sessions · 1 with materials online
Natural language processing and the attention mechanism, worked through real examples.
Introduction to Natural Language Processing
The first workshop of Winter 2023: basic NLP libraries and common text pre-processing tasks.
Attention Mechanism in Deep Learning
Attention mechanisms for time-series forecasting, worked through a traffic-flow prediction example.
2021–22Machine learning, step by step7 sessions · 6 with materials online
Scientific Python, then regression, classification and feature engineering, then neural networks. Every session has its notebook on Kaggle and most have a recording.
Introduction to Scientific Python
NumPy, Pandas, scikit-learn and matplotlib for beginners.
Linear Regression
What linear regression is, when it is useful and how it works, as part of a series preparing members for the CAIS X competition.
Linear Classification
An introduction to linear classifiers, focusing on logistic regression.
Feature Selection & Transformation
Techniques for selecting and transforming features to improve model quality and performance.
Intro to Neural Networks
The foundations of deep learning: how simple parts combine into neural networks that can model complex relationships.
Neural Networks Project 1: Build Your First Neural Network
Build, train and test a simple neural network that makes predictions from tabular data.
Intro to Convolutional Neural Network (CNN)
The core ideas behind CNNs and the architectures behind image classification, object detection and segmentation.
2020–21Data science fundamentals7 sessions · 7 with materials online
The club's first full series, run online and recorded: Python and data science from a first Kaggle submission to clustering and dimensionality reduction.
Introduction to Python and Data Science
A beginner session on what data science is, Python basics, Kaggle and Jupyter notebooks.
First Kaggle Competition Submission
How to navigate Kaggle, then build and submit a first notebook for the CAIS X competition.
Maximum Likelihood Estimation Lecture
Introduced Maximum Likelihood Estimation and derived it for the Bernoulli and Gaussian distributions, touching on the bias-variance dilemma along the way.
Feature Engineering Techniques
Basic feature engineering techniques for improving model performance: garbage in, garbage out.
Introduction to Scientific Python
The core data science toolkit: NumPy, Pandas, scikit-learn and matplotlib.
Clustering: K-means vs. Gaussian Mixture Models
Unsupervised learning through K-means and Gaussian Mixture Models, and how Expectation-Maximization fits a GMM.
Dimensionality Reduction: PCA vs. LDA
Derived Principal Component Analysis and Linear Discriminant Analysis and compared their strengths and limits. Streamed live on Twitch.
Outside a series
One-off workshops
Sessions run at hackathons and on their own, outside a series.
- cuHacking AI WorkshopHackathon workshop on using Ollama and HuggingFace models in your projects, plus mentorship on site.
- Metrics 101How to calculate and interpret metrics, with use cases for machine learning and data science projects.
- CPA Ontario × CAIS: Power BI WorkshopA demonstration of the Power BI business analytics tool followed by hands-on practice, run with club sponsor CPA Ontario.
- Visual Mapping of Data using PythonA hands-on tutorial on plotting datasets onto real maps with Pandas, Basemap and NumPy.
- Intro to Data Science WorkshopAn introductory workshop for students new to data science and machine learning. Attendees were asked to bring a laptop.