An artificial neural network (ANN) is a parameterized machine learning model used to approximate complex functions.
It consists of multiple layers of interconnected processing units called neurons, typically including an input layer, one or more hidden layers, and an output layer.
Each connection between neurons has an associated weight. During training, these weights are adjusted to minimize a loss function, commonly using gradient descent and backpropagation.
Neural networks are capable of modeling complex patterns in large datasets and form the foundation of modern deep learning methods used in computer vision, speech recognition, and natural language processing.
Definition:
An artificial neural network is a computational model composed of interconnected artificial neurons that learn from data by adjusting weighted connections to approximate complex relationships.
Source:
Goodfellow, Bengio, Courville – Deep Learning, MIT Press; and standard literature on artificial neural networks in machine learning.