Machine learning is a branch of AI where systems learn patterns from data instead of being explicitly programmed.

Deep learning uses multi-layered neural networks to learn complex patterns directly from raw data.

AI is the broad goal, machine learning is one approach to it, and deep learning is a specific technique within machine learning.

A model is the trained mathematical structure that maps inputs to outputs based on learned patterns.

A dataset is the collection of examples used to train, validate, or evaluate a model.

Parameters are the internal values a model learns during training that determine its behavior.

Training is the process of adjusting a model's parameters so its predictions get closer to the correct answers.

Inference is using a trained model to produce predictions or outputs on new data.

A neural network is a layered system of connected nodes that learns to transform inputs into outputs.

A GPU is specialized hardware that performs the parallel matrix computations AI models rely on far faster than a CPU.