0% found this document useful (0 votes)
6 views7 pages

Syllabus Test

The Canada AI Olympiad (CAIO) 2026 consists of a National Qualifier on November 23, 2025, followed by a National Training Camp in January 2026 for selected students. Eligibility is open to full-time secondary school students globally, but only those in Canadian schools can represent Canada at the IAIO 2026 competition. The competition includes two rounds focusing on AI fundamentals and applied problem solving, with various topics covered in the syllabus such as supervised learning, unsupervised learning, and reinforcement learning.

Uploaded by

spenceryuan0426
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
6 views7 pages

Syllabus Test

The Canada AI Olympiad (CAIO) 2026 consists of a National Qualifier on November 23, 2025, followed by a National Training Camp in January 2026 for selected students. Eligibility is open to full-time secondary school students globally, but only those in Canadian schools can represent Canada at the IAIO 2026 competition. The competition includes two rounds focusing on AI fundamentals and applied problem solving, with various topics covered in the syllabus such as supervised learning, unsupervised learning, and reinforcement learning.

Uploaded by

spenceryuan0426
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

Basic Information
Competition Structure
CAIO 2026 is a two-stage competition consisting of the National Qualifier and the National Training
Camp.
• The CAIO National Qualifier will be held in November 23, 2025
• Selected students will be invited to the CAIO National Training Camp in January 2026
Each stage includes two 90-minute rounds:
• Round 1: AI Fundamentals Challenge
• Round 2: Applied Problem Solving
For detailed schedules and content outlines, please refer to this page and the “Prepare” page.

Registeration Period
Registration is from July to October 31, 2025.

Eligibility
The competition is open to individuals only, with no restrictions on nationality.
• For the CAIO National Qualifier, all students currently enrolled full-time in secondary schools
[Link] 1/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

(Grades 7–12), regardless of country, are eligible to participate.


• Students advancing to the CAIO National Training Camp may include both Canadian and
international students. However, only students who are enrolled full-time in Canadian secondary
schools are eligible to be selected for the CAIO National Team and represent Canada at the IAIO
2026 competition.

Timeline
November 23rd 2025 Beginning Of Janua

CAIO National Qualifier CAIO National Trainin


All secondary school students are invited to An invite-only, multi-day in-person tra
participate in the CAIO national qualifier on November selection program held in the second
23, 2025 (subject to change). 2026, the camp features expert-led le
competition-style tests.
Participates achieving top results will be recognized ​ 
with official CAIO certificates in three levels of At the end of the camp, four gold, fou
distinction: Distinguished Honor Roll (top 5%), Honor bronze medals will be awarded based
Roll (top 20%), and Certificate of Distinction (top performance. All others will receive th
50%). The top 20 participates will be invited to join the participation. The top four contestants
CAIO National Training Camp. to represent Canada at the 2026 IAIO

[Link] 2/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

Syllabus
1. Data Preparation 

Data Processing
Python Pandas
Python Numpy
Linear algebra fundamentals
Exploratory data analysis (EDA)
Data Visulization
Python Matpolitlib
Python Seaborn

2. Supervised Learning 

Regression Models
Linear regression (Least Squares, Gradient Descent)
Polynomial regression
Classification Models
Decision Trees (entropy, information gain)
Support Vector Machines (SVM) and hyperplanes
Naïve Bayes classification
Regularization & Overfitting
L1 (Lasso) and L2 (Ridge) Regularization
Cross-validation techniques

3. Unsupervised Learning 

Clustering
K-means clustering (cost function minimization)
Hierarchical clustering
Gaussian Mixture Models (GMM)
[Link] 3/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

Dimensionality Reduction
PCA and its application in visualization
t-SNE for high-dimensional data representation

4. Reinforcement Learning 

Markov Decision Processes (MDPs)


States, actions, rewards
Bellman Equations
Q-Learning
Temporal Difference Learning
Exploration vs. exploitation

5. AI Search 

Uninformed Search
Breadth-First Search (BFS), Depth-First Search (DFS)
Uniform Cost Search
Informed Search
A* Algorithm and heuristics
Minimax search (game AI)

6. Logical Reasoning 

Propositional & First-Order Logic


CNF, logical connectives
Unification in inference
Resolution Theorem Proving
Satisfiability and SAT solvers

7. Evaluation of ML Models 

Classification Metrics
[Link] 4/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

Precision, recall, F1-score


ROC-AUC curves
Bias-Variance Tradeoff
Overfitting detection
K-fold cross-validation

8. Constraint Satisfaction Problems 

Backtracking & Constraint Propagation


AC-3 algorithm
Forward checking

9. Kernel Methods 

Support Vector Machines (SVM)


Margin maximization
Soft-margin vs. hard-margin SVM
Kernel Trick
Transforming low-dimensional data to high-dimensional space
Radial Basis Function (RBF) kernel

10. Recommender Systems 

Collaborative Filtering
User-based and item-based filtering
Similarity metrics (cosine similarity, Pearson correlation)
Content-Based Filtering
TF-IDF and word embeddings
Feature engineering for recommendation models
Hybrid Recommender Systems
Combining collaborative and content-based filtering
Matrix factorization (SVD, ALS algorithms)

[Link] 5/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

Deep learning approaches (Neural Collaborative Filtering, Autoencoders for


recommendations)

Resources
Here are some resources that will be useful when preparing for the CAIO contest.
We expect participants who do well in the contest to have some knowledge of the following areas.

Python

Python Official Documentation scikit-learn: Machine Learning in Python

PyTorch

Intro to PyTorch tutorial

Machine Learning

Stanford CS229: Machine Learning on Youtube


Machine Learning Specialization

[Link] 6/7
1/9/26, 7:08 PM Participate – Canada AI Olympiad (CAIO)

IAIO Webinars

IAIO Official Webinars

EMAIL US FOLLOW US © Copyright


CAIO 2026 | All
info@iaio-
RIGHTS
[Link]
RESERVED |

Privacy policy

[Link] 7/7

You might also like