Skip to main content

Artificial Intelligence

From classic search algorithms to modern transformers, this section builds up the theory and intuition behind AI systems — with interactive visualizers for the parts that are hardest to grasp from equations alone.

Planned Topics​

Search & Classical AI​

  • Uninformed search: BFS, DFS, iterative deepening
  • Informed search: A*, heuristics, admissibility
  • Adversarial search: Minimax, alpha-beta pruning — interactive game tree

Machine Learning Fundamentals​

  • Supervised vs. unsupervised vs. reinforcement learning
  • Bias-variance tradeoff — interactive demo
  • Train/validation/test split and why it matters
  • Gradient descent: batch, stochastic, mini-batch — loss surface visualizer

Neural Networks​

  • The perceptron and its limits
  • Backpropagation — step-by-step interactive walkthrough
  • Activation functions: sigmoid, ReLU, GELU
  • Vanishing/exploding gradients and normalization (BatchNorm, LayerNorm)

Convolutional Networks​

  • Convolution as feature detection — interactive filter visualizer
  • Pooling and receptive field
  • ResNet skip connections

Transformers & Attention​

  • Self-attention — interactive query/key/value demo
  • Multi-head attention and positional encoding
  • The transformer block
  • How GPT/BERT differ

Reinforcement Learning​

  • Markov decision processes
  • Q-learning and the Bellman equation
  • Policy gradient methods
  • Exploration vs. exploitation

Pages coming soon — check back or contribute a page using the template.