Foundations
Neural Network
A model loosely inspired by the brain, built from layers of simple units that each pass signals to the next.
A neural network is made of interconnected nodes, often called neurons, organized in layers. Each connection has a weight that strengthens or weakens the signal passing through it, and the network learns by nudging those weights until its outputs match the examples it was trained on. The brain analogy is loose, but the idea of many simple units combining into complex behavior is the core of how modern AI works.
Reference: Wikipedia: Neural Network
Related terms
Deep Learning
Machine learning built on large neural networks with many layers, which is what powers most recent AI breakthroughs.
Weights
The individual strengths of the connections in a neural network, which are what actually change as a model learns.
Backpropagation
The algorithm that figures out how to adjust each weight in a network to reduce its errors.
Parameters
The adjustable numbers inside a model that get tuned during training and store what the model has learned.