Which statement best describes a neural network?

• A. A single neuron model used for simple linear forecasting.
• B. A series of interconnected neurons; typically input, one or more hidden layers, and an output layer.
• C. A rule-based expert system with no learned parameters.
• D. A decision tree used for regression.

Answer: (B)

A neural network is a collection of simple processing units called neurons arranged in layers, with data flowing from inputs through one or more hidden layers to an output layer. Each neuron computes a weighted sum of its inputs, applies a nonlinear activation, and passes the result to the next layer, with learning occurring by adjusting the weights during training. This layered, interconnected structure lets the network learn complex, nonlinear relationships from data—something a single neuron cannot do alone. A rule-based expert system doesn’t learn from data, and a decision tree uses a different structure and learning approach, not layered neurons.