Neural Network

A series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.

How it works

A neural network is organised in layers of interconnected nodes (neurons). Each connection has a weight; each neuron computes a weighted sum of its inputs and applies an activation function. The output layer produces the prediction. During training, backpropagation computes gradients of the loss with respect to each weight, and an optimiser updates the weights to reduce errors. Deep neural networks stack many layers, enabling them to learn hierarchical feature representations from raw data.

Why it matters

Neural networks are the foundation of the modern AI revolution. Their ability to learn complex, non-linear functions from data — without manual feature engineering — has enabled breakthroughs in every perceptual and cognitive domain: vision, speech, language, game playing, and protein structure prediction. Understanding neural networks is the prerequisite for understanding any modern AI system, from the simplest image classifier to the most powerful language model.