Behind the AI

The Prediction Problem

Almost every machine-learning task, at its core, reduces to the same mathematical problem: given a set of input variables, predict the value of the output variables.

Traditional Programming vs. Machine Learning

In traditional programming a human writes the rules; in machine learning you feed the machine examples and it works out the rules for itself.

How Machines Learn: Weights, Loss, and Gradient Descent

A machine-learning system learns by adjusting its weights to make the loss — the number that measures the total prediction error — as small as possible, using an optimization algorithm, typically gradient descent.

Overfitting vs. Generalization

A model that fits its training data perfectly can still be useless: the goal isn't zero error but generalization — predicting unseen cases as well as possible — which means resisting the temptation to overfit.

The Three Flavors of Machine Learning

Machine learning can be traced back to three broad families — supervised, unsupervised, and reinforcement learning — set apart by what the training data looks like: labeled, unlabeled, or replaced by rewards.

Anatomy of a Neural Network

A neural network is a model made of elementary nodes arranged in layers and joined by weighted connections: data enters through the input layer, passes through one or more hidden layers, and exits through the output layer — and the connection weights are exactly the parameters that training has to find.

The Artificial Neuron

An artificial neuron computes a weighted sum of its inputs, adds a bias, and passes the result through an activation function: it is the non-linearity of that function that makes depth meaningful, because without it an entire network would collapse into a single linear operation.

Backpropagation: How Millions of Weights Get Adjusted

Why Neural Networks Are So Powerful — and So Opaque

A Field Guide to Neural Network Types

Can a Number Mean Something?

Word2Vec and Context Learning

What Embeddings Reveal

Tokenization: Breaking Text Into Pieces

Attention and Parallel Computing — Why Transformers Scale

How a Transformer Predicts the Next Word

Why the Same Prompt Gives Different Answers

Knowledge vs. Pattern Matching: What's Actually Happening?

The Scaling Laws: Why Bigger Models Get Better

Emerging Capabilities: When Scale Changes Everything

In-Context Learning and Few-Shot Prompting

Chain of Thought: How "Let's Think Step by Step" Unlocked Reasoning

RAG: Giving LLMs a Memory Beyond Training

Automations vs. AI Workflows vs. AI Agents

Hallucinations: Why LLMs Lie

When NOT to Use an LLM

Small Language Models

Mixture of Experts, Quantization, and Distillation

Diffusion Models: A Different Way to Generate