A neural network is a computational model inspired by the way biological neural networks in the human brain process information. It consists of interconnected groups of artificial neurons (also called nodes) that work together to process data and recognize patterns. Neural networks are a key component of machine learning and deep learning technologies.
Articles by others on the same topic
An artificial neural network is a parameterized system of interconnected computational units whose outputs depend on weighted inputs. A feedforward neural network commonly composes layerswhere are weight matrices, are biases and are activation functions. Recurrent neural networks instead reuse a state through time; weight sharing also imposes structure in a convolutional neural network.
A loss function measures how well outputs serve the task. Backpropagation applies the chain rule to compute parameter gradients, which an optimization algorithm can use for learning. For example, a hidden rectified unit followed by a weighted output represents a piecewise affine function. With identity activations in every hidden layer, successive affine maps collapse to one affine map, so depth alone adds no nonlinear expressiveness.
The useful representation depends on architecture, data and training. Fitting many parameters does not establish generalization; regularization, independent evaluation and the target data distribution remain relevant.
