Announcements
Beaver-Edge AI Institute
Beaver-Edge AI Institute

AI Courses

124USAAIO Round 2 Qualifiers晋级USAAIO第二轮
78USAAIO Round 2 MedalistsUSAAIO第二轮获得奖牌
17USAAIO CampersUSAAIO国家集训队
27AI Olympiad National Team Members Worldwide各国AI奥赛国家队队员
46IOAI/IAIO/IAI²O MedalistsIOAI/IAIO/IAI²O获奖
From foundations to international competition

Curriculum Pathway to AI Olympiad Goals

Complete curriculum

AI Course Details

Search or select coursesAll courses
AI 100

AI 100 Programming with Google Colab

Course contents

  • Markdown programing: Text formatting
  • Markdown programing: Writing code
  • Markdown programing: Writing AI-related math
  • Markdown programing: Writing tables
  • Writing md files in ipynb files
  • Writing py files in ipynb files

Prerequisite(s)

  • None

Takeaways after completing this course

  • Be ready to write solutions in paper-based competition (solutions shall be written on ipynb files, such as Google Colab text cells)
  • Be ready to take AI 200 Mathematical Methods for AI

Duration

  • 2 hours

FAQs

Register
AI 20J

AI 20J Conceptual Linear Algebra for AI: An Intuitive, Visual, and Beginner-Friendly Approach

Course contents

  • Vectors
  • Inner product and similarity
  • Outer product
  • Vector space
  • Basis vectors
  • Matrices
  • Matrix multiplication
  • Linear transformation
  • Eigenvalues and eigenvectors
  • Singular value decomposition

Prerequisite(s)

  • K-12 math course: Algebra 1, Geometry

Takeaways after completing this course

  • Be ready to take AI 200 - Mathematical Methods for AI
  • Be ready to take AI 30J - A primer in Machine Learning

FAQs

Register
AI 200

AI 200 Mathematical Methods for AI

Course contents

  • Linear algebra
  • Space, subspace, basis, orthonormal vectors
  • Vector/matrix operations
  • Eigenvalues, eigenvectors
  • Matrix d ecompositions
  • Calculus
  • Single-variable derivatives
  • Multi-variable derivatives and gradients
  • Chain rule
  • Probability and statistics
  • Discrete distributions
  • Continuous distributions
  • Mean
  • Variance, covariance
  • Bayes' rule
  • Convex optimization
  • Convexity
  • Gradient descent
  • Duality

Prerequisite(s)

  • AI 100 Markdown Programming for AI
  • K-12 math course: Algebra 2
  • Prerequisite test: Click here

Takeaways after completing this course

  • Be on the halfway of earning Honor Rolls in USAAIO Round 1
  • Be ready to take AI 210 Coding for AI 1 - Advanced Python Techniques and Fundamental AI Libraries

Duration

  • 20 hours

FAQs

Register
AI 210

AI 210 Coding for AI 1 - Advanced Python Techniques and Fundamental AI Libraries

Course contents

  • Advanced Python techniques for AI
  • NumPy
  • Pandas
  • Matplotlib
  • Seaborn

Prerequisite(s)

  • AI 100 Markdown Programming for AI
  • AI 200 Mathematical Methods for AI
  • Prerequisite test: Click here

Takeaways after completing this course

  • Be ready to earn Honor Rolls in USAAIO Round 1
  • Be ready to take AI 300 Machine Learning 1

Duration

  • 20 hours

FAQs

Register
AI 30J

AI 30J A Primer in Machine Learning: An Intuitive, Visual, and Beginner-Friendly Approach

Course contents

  • Data representation
  • Loss functions
  • Supervised learning
  • Tree models and ensemble methods
  • Bias and variance tradeoff
  • Overfitting and underfitting
  • Unsupervised learning
  • Semi-supervised learning
  • Time series analysis
  • Deep neural networks
  • Architectures of classical deep neural works
  • Evaluation, fairness, model selection
  • Pipeline of doing machine learning tasks

Prerequisite(s)

  • AI 20J

Takeaways after completing this course

  • Be ready to take AI 300 - Machine Learning 1

FAQs

Register
AI 300

AI 300 Machine Learning 1

Course contents

  • Linear regression
  • Bias-variance trade-off
  • Regularization
  • Kernel methods
  • k-nearest neighbors
  • Cross validation
  • Logistics regression

Prerequisite(s)

  • AI 200 Mathematical Methods for AI
  • AI 210 Coding for AI 1 - Advanced Python Techniques and Fundamental AI Libraries
  • Prerequisite test: Click here

Takeaways after completing this course

  • Be on the half way of earning High Honor Rolls in USAAIO Round 1
  • Be ready to take AI 400 Machine Learning 2

Duration

  • 20 hours

FAQs

Register
AI 310

AI 310 Coding for AI 2 - PyTorch

Course contents

  • Tensors
  • Autograd
  • Devices
  • Modules
  • Datasets
  • Dataloader, collation
  • Losses
  • Optimizers

Prerequisite(s)

  • AI 210 Coding for AI 1 - Advanced Python Techniques and Fundamental AI Libraries
  • Prerequisite test: Click here

Takeaways after completing this course

  • Be ready to earn High Honor Rolls in USAAIO Round 1
  • Be ready to take AI 410 Deep Learning and Computer Vision 1

Duration

  • 20 hours

FAQs

Register
AI 40J

AI 40J A Primer in Deep Learning: A Visual and Beginner-Friendly Approach

Course contents

  • From machine learning to deep learning: what depth adds
  • Neural networks as layered transformations from inputs to predictions
  • Activation functions and how networks learn nonlinear patterns
  • Loss functions, forward propagation, and backpropagation—conceptually and visually
  • Training, validation, overfitting, and practical model improvement
  • Convolutional neural networks and visual feature learning
  • A beginner-friendly deep learning workflow with no heavy mathematics

Prerequisite(s)

  • AI 30J A Primer in Machine Learning

Takeaways after completing this course

  • Be ready to take AI 410 Deep Learning and Computer Vision 1

FAQs

Register
AI 400

AI 400 Machine Learning 2

Course contents

  • Support vector machines
  • Decision trees
  • Random forest
  • Boosting
  • Dimensionality reduction
  • Principal component analysis
  • t-SNE
  • UMAP
  • k-means clustering
  • Time-series analysis

Prerequisite(s)

  • AI 300 Machine Learning 1

Takeaways after completing this course

  • Be on the half way of earning Distinguished Honor Rolls in USAAIO Round 1
  • Be ready to take AI 410 Deep Learning and Computer Vision 1

Duration

  • 20 hours

FAQs

Register
AI 410

AI 410 Deep Learning 1

Course contents

  • Deep learning foundations
  • Multi-layer perceptron model
  • Forward propagation
  • Activation functions
  • Adaptive moment estimation
  • Backpropagation
  • Parameter initialization
  • Dropout
  • Computer vision
  • Convolutional layers
  • Pooling layers
  • Batch normalization
  • Convolutional neural network
  • Image data augmentation
  • VGG
  • ResNet
  • GoogLeNet
  • Pretrained models
  • Transfer learning
  • Fine tuning

Prerequisite(s)

  • AI 300 Machine Learning 1
  • AI 310 Coding for AI 2 - PyTorch
  • Prerequisite test: Click here

Takeaways after completing this course

  • Be ready to earn Distinguished Honor Rolls in USAAIO Round 1
  • Be ready to take AI 500 Deep Learning 2

Duration

  • 20 hours

FAQs

Register
AI 500

AI 500 Deep Learning 2

Course contents

  • Transformers
  • Self-attention
  • Cross-attention
  • Masked self-attention
  • Layer normalization
  • Word embedding
  • Positional encoding
  • Inference
  • Training
  • Batch processing
  • Pre-training
  • Fine-tuning
  • Linear attention
  • Flash attention
  • Gated attention
  • kv cache
  • Applications of transformer models

Prerequisite(s)

  • AI 400 Machine Learning 2
  • AI 410 Deep Learning 1

Takeaways after completing this course

  • Be on the way of earning medals in USAAIO Round 2
  • Be on the way of potentially qualify for USAAIO training camp
  • Be on the way of potentially qualify for being on national team for international Olympiads
  • Be ready to take AI 510 Deep Learning 3

Duration

  • 20 hours

FAQs

Register
AI 510

AI 510 Deep Learning 3

Course contents

  • Recurrent neural network
  • Models
  • Applications
  • Natural language processing
  • Character tokenization
  • Subword tokenization
  • Word tokenization
  • Word embedding method: Skip-gram
  • Word embedding method: Continuous bag of words
  • Word embedding method: Global vectors
  • Encoder-only transformers: BERT
  • Decoder-only transformers: GPT
  • Case study: IOAI contest problems
  • Graph neural networks
  • Message-passing neural networks
  • Graph convolutional networks
  • Graph attention networks
  • Advanced deep neural network models
  • Vision transformers
  • Physics-informed neural networks

Prerequisite(s)

  • AI 500 Transformers

Takeaways after completing this course

  • Be on the way of earning medals in USAAIO Round 2
  • Be on the way of potentially qualify for USAAIO training camp
  • Be on the way of potentially qualify for being on national team for international Olympiads
  • Be ready to take AI 520 Deep Learning 4

Duration

  • 20 hours

FAQs

  • FAQs will be added as they become available.
Register
AI 520

AI 520 Deep Learning 4

Course contents

  • Contrastive language-Image pre-training
  • Adversarial attack
  • Object detection
  • Autoencoder
  • UNet
  • Generative AI
  • Variational autoencoder
  • Generative adversarial network
  • Denoising diffusion probabilistic method
  • Stable diffusion

Prerequisite(s)

  • AI 510 Deep Learning 3

Takeaways after completing this course

  • Be ready to earn medals in USAAIO Round 2
  • Potentially qualify for USAAIO training camp
  • Potentially qualify for being on national team for international Olympiads

Duration

  • 20 hours

FAQs

Register
AI 900

AI 900 Grandmaster Course

Course contents

  • Advanced topics beyond all courses at 100-500 levels

Prerequisite(s)

  • All courses at 100-500 levels

Takeaways after completing this course

  • Qualify for being on your country's national training camp
  • Qualify for being on your national team to represent your country for IOAI and IAIO
  • Earn a medal (ideally a gold medal ) in IOAI and IAIO

Eligibility to enroll in this course

  • Master all contents in 100-500 level courses
  • Have a strong established record

Duration

  • 20 hours

FAQs

  • FAQs will be added as they become available.
Register
AI 910

AI 910 Advanced AI Open-Ended Challenge Collection

Course contents

  • More than 200 open-ended AI exercise problems at easy, medium, and difficult levels
  • Training, validation, and test datasets for each problem
  • Develop, evaluate, compare, and improve model solutions using the evaluation score specified for each problem
  • Traditional machine learning and modern AI methods across tabular, image, video, audio, and text data
  • Problem-specific model constraints, including restrictions on deep learning or pretrained models

Prerequisite(s)

  • All courses at the 100–500 levels

Takeaways after completing this course

  • Prepare to qualify for your country's national training camp
  • Prepare to qualify for your national team to represent your country at IOAI and IAIO
  • Develop the problem-solving skills needed to earn a medal, ideally gold, at IOAI and IAIO

FAQs

Register

Join our email list

Beaver-Edge AI Institute

Download Our Brochure (下载我们的介绍手册)

Tell us who you are to access the English and Chinese brochures.