Foundations

Artificial Intelligence is software that performs tasks we normally associate with human intelligence.

Machine learning is AI that learns patterns from data instead of being explicitly programmed with rules.

Deep learning is machine learning using many-layered neural networks that learn features automatically.

A neural network is a web of simple math units ("neurons") that transform inputs into outputs and learn by adjusting connection weights.

A model is the trained artifact that stores what an AI system learned and turns new inputs into predictions.

Training is teaching a model from data; inference is using the trained model to make predictions.

Parameters are numbers a model learns from data; hyperparameters are knobs you set before training, like learning rate and size.

A dataset is a table of examples: features are the input columns, labels are the answers the model should predict.

A loss scores how wrong a prediction is so training can shrink that number; MSE and cross-entropy are the usual workhorses.

Gradient descent walks downhill on the loss by subtracting a step times the slope — that is how models update parameters.

Backpropagation applies the chain rule through each layer so every weight gets a gradient; then gradient descent can step.