Highschool ML Course

created by the SHSID Data Science Club

---

A Machine Learning course specifically for highschool students based on the USAAIO course provided by Beaver-Edge AI.

For the best experience, download the repo and run the ipynb for better visualization!

---

Table of Contents

0. Prerequisites

• 0.1. Basic Environment For Python
• 0.2. Python For AI
  • 0.2.1. Advanced Python Techniques For AI
  • 0.2.2. NumPy
  • 0.2.3. Pandas
  • 0.2.4. Matplotlib
  • 0.2.5. Seaborn

1. Mathematical Methods For AI

• 1.1. Linear Algebra
• 1.2. Calculus
  • 1.2.1. Single-Variable Derivatives
  • 1.2.2. Multi-Variable Derivatives & Gradients
  • 1.2.3. Chain Rule
• 1.3. Probability & Statistics
  • 1.3.1. Discrete Distributions
  • 1.3.2. Continuous Distributions
  • 1.3.3. Mean
  • 1.3.4. Variance, Covariance
  • 1.3.5. Bayes' Rule
• 1.4. Convex Optimization
  • 1.4.1. Convexity
  • 1.4.2. Gradient Descent
  • 1.4.3. Duality

2. Machine Learning Generics

• 2.0. Machine Learning Terminology
• 2.1. Linear Regression & Logistic Regression
• 2.1. Support Vector Machines
• 2.3. Regularization, Bias-Variance Trade-Off, Kernel Methods, Cross Validation
• 2.4. Principal Component Analysis, Dimensionality Reduction
• 2.5. Decision Trees, Random Forests
• 2.5. K-Nearest Neighbors, Clustering K-Means
• 2.7. Boosting

3. PyTorch

• 3.1. Tensors
• 3.2. Autograd
• 3.3. Devices
• 3.4. Modules
• 3.5. Datasets
• 3.6. Dataloader
• 3.7. Losses
• 3.8. Optimizers

4. Deep Learning & Computer Vision

• 4.1. Forward Propagation, Activation Functions, Linear Layer
• 4.2. Backpropagation, Gradient Descent, Adaptive Moment Estimation
• 4.3. Parameter Initialization, Batch Normalization, Dropout
• 4.4. Convolutional Layers, Pooling Layers, Convolutional Neural Network
• 4.5. Image Data Augmentation
• 4.6. VGG
• 4.7. ResNet
• 4.8. GoogLeNet
• 4.9. Transfer Learning

5. Transformers

• 5.1. Self-Attention, Cross-Attention, Masked Self-Attention, Layer Normalization, Word Embedding, Positional Encoding
• 5.2. Inference
• 5.3. Training, Pre-Training, Fine-Tuning
• 5.4. Batch Processing
• 5.5. BERT, T5, GPT

6. Natural Language Processing & Graph Neural Networks

• 6.1. Character, Subword & Word Tokenization
• 6.2. Word Embedding Methods
• 6.3. Skip-Gram, Continuous Word Bag, Global Vectors
• 6.4. Encoder-Only & Decoder-Only Transformers
• 6.5. Message-Passing Neural Networks
• 6.6. Graph Convolutional Networks
• 6.7. Vision Transformers

7. OpenCV & Generative AI

• 7.1. Object Detection
• 7.3. UNet
• 7.4. Autoencoder, Variational Autoencoder
• 7.5. Generative Adversarial Network, Adversarial Attack
• 7.8. Stable Diffusion, Denoising Diffusion Probabilistic Methods