Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Neural network (machine learning)
open-in-new
<p>In <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a>, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks. </p><p>A neural network consists of connected units or nodes called <i><a href="/facts/Artificial_neuron/TSH6nsgg">artificial neurons</a></i>, which loosely model the <a href="/facts/Neuron/G7CyTVdH">neurons</a> in the brain. Artificial neuron models that mimic biological neurons more closely have also been recently investigated and shown to significantly improve performance. These are connected by <i>edges</i>, which model the <a href="/facts/Synapse/vdMRJCUn">synapses</a> in the brain. Each artificial neuron receives signals from connected neurons, then processes them and sends a signal to other connected neurons. The "signal" is a <a href="/facts/Real_number/R02gw5Pb">real number</a>, and the output of each neuron is computed by some non-linear function of the sum of its inputs, called the <i><a href="/facts/Activation_function/S4NImL6L">activation function</a></i>. The strength of the signal at each connection is determined by a <i><a href="/facts/Weighting/HUltmeDW">weight</a></i>, which adjusts during the learning process. </p><p>Typically, neurons are aggregated into layers. Different layers may perform different transformations on their inputs. Signals travel from the first layer (the <i>input layer</i>) to the last layer (the <i>output layer</i>), possibly passing through multiple intermediate layers (<i><a href="/facts/Hidden_layer/uKzUskIX">hidden layers</a></i>). A network is typically called a deep neural network if it has at least two hidden layers. </p><p>Artificial neural networks are used for various tasks, including <a href="/facts/Predictive_modeling/VI5ThSKa">predictive modeling</a>, <a href="/facts/Adaptive_control/9CUsn1wv">adaptive control</a>, and solving problems in <a href="/facts/Artificial_intelligence/lJGauQwX">artificial intelligence</a>. They can learn from experience, and can derive conclusions from a complex and seemingly unrelated set of information. </p>