AI Explained
How modern AI works, from neural networks to large language models.
Foundations
Core ideas: data, models, training, and evaluation.
How Machine Learning Works: Data, Models and Learning from Examples
Machine learning fits a model to examples by adjusting parameters to shrink error. Learn how data, loss functions and gradient descent work together.
BasicsWhy Models Overfit and How Training, Validation and Test Sets Catch It
Overfitting means a model memorized training examples instead of general patterns. Data splits, cross-validation and regularization catch and reduce it.
Neural Networks
Neurons, layers, backpropagation and architectures.
Activation Functions: Why Neural Networks Need Nonlinearity
Activation functions add the nonlinearity neural networks need. Compare sigmoid, tanh, ReLU and GELU by output range and gradient behavior.
Neural NetsHow Backpropagation Trains Neural Networks, Step by Step
Backpropagation uses the chain rule to find how each weight affects the loss, then updates the weights. Follow one worked example with real numbers.
Language Models
Transformers, tokens, attention and how chatbots work.
How Attention Works in Transformers: Queries, Keys and Values Explained
Attention lets each token weigh every other token when building its representation. Learn queries, keys, values, softmax weights and multi-head attention.
LLMsHow Tokenization Works: Turning Text into Numbers for Language Models
Language models read tokens, not letters or words. Learn how byte pair encoding splits text into subword pieces and why tokens set cost and context size.
Computer Vision
How machines see: CNNs, detection and image generation.
How Convolutional Neural Networks Work
Learn how convolutional neural networks scan images with small filters, build features layer by layer, and classify what they see.
VisionHow Object Detection Works in Computer Vision
Understand how object detectors find and label many objects in one image using bounding boxes, IoU, and non-maximum suppression.
Using AI
Practical guides to prompting, local models and AI workflows.
How to Run Large Language Models Locally
Learn what hardware, memory and quantization decide whether a language model runs on your own computer, and which tools to start with.
ToolsHow to Write Effective Prompts for AI Models
Learn how prompts steer language models, which parts make a prompt clear, and how to iterate for reliable answers.
AI Safety & Ethics
Alignment, bias, risks and responsible use.
How Bias Enters AI Systems and How to Reduce It
Learn where bias in machine learning comes from, including data, labels and proxies, and which checks help teams measure and reduce it.
SafetyWhat Is AI Alignment and Why It Matters
Understand AI alignment, the problem of getting AI systems to pursue the goals people actually intend, and the main approaches researchers use.