neural network

American  

[noor-uhl net-wurk, nyoor-uhl] / ˈnʊr əl ˈnɛtˌwɜrk, ˈnyʊr əl /

noun

1. any group of neurons that conduct impulses in a coordinated manner, as the assemblages of brain cells that record a visual stimulus.

2. Also called neural net.  Computers. a hardware or software system in which weighted connections between data nodes are refined to produce increasingly accurate results in information processing, as in pattern recognition or problem solving, with the goal of algorithmic computing that requires minimal human intervention.

---

neural network British  

noun

1. an interconnected system of neurons, as in the brain or other parts of the nervous system

2. Also called: neural net.  an analogous network of electronic components, esp one in a computer designed to mimic the operation of the human brain

---

Etymology

Origin of neural network

First recorded in 1985–90

Example Sentences

“We spent years developing the mathematical theory required to compress a neural network without losing its reasoning capabilities,” said Hassibi, chief executive of the venture.

From The Wall Street Journal • Mar. 31, 2026

"Based on the principle of polarization holography, we used a deep learning architecture known as a convolutional neural network model to enable the use of polarization as an independent information dimension."

From Science Daily • Mar. 29, 2026

They are credited with proposing the first mathematical model of a neural network to explain how the brain’s biological connectivity produces complexity—thus leading to a computational theory of the mind.

From The Wall Street Journal • Mar. 29, 2026

"In addition, neural network synchronous decoding reduced the need for complex measurements and step-by-step reconstruction, supporting more efficient readout and decoding. This could enable a practical route toward high-capacity, high-throughput holographic data storage."

From Science Daily • Mar. 29, 2026

And these technological therapies would have to be constructed, she said, so that they don’t invite their own side effects, like, say, overbuilding one neural network.

From "A Deadly Wandering: A Mystery, a Landmark Investigation, and the Astonishing Science of Attention in the Digital Age" by Matt Richtel