= ANN искусственная нейронная сеть, ИНС программа или аппаратура, моделирующие сеть, построенную на принципах взаимодействия клеток (нейронов) нервной системы человека. В аппаратной реализации ИНС представляет собой сеть из множества простых процессоров (units, формальных нейронов), объединённых в слои. Каждый формальный нейрон имеет небольшую локальную память и коммуникационные соединения с другими нейронами (connections) предыдущего слоя обработки данных. По входным соединениям передаются числовые данные, а по выходным - результаты их обработки. Такие сети используются для распознавания образов, речи, прогнозирования ситуации в финансовой сфере и т. д. Если не оговорено другое, синоним - neural network Смотри также: AI, artificial life, computer vision, speech recognition, speech synthesis, training Например: An artificial neural network can be built by interconnecting simple processing units that model biological neurons — Искусственную нейронную сеть можно построить путём соединения простых процессорных блоков, моделирующих биологические нейроны
(ANN, commonly just "neural network" or "neural net") A network of many very simple processors ("units" or "neurons"), each possibly having a (small amount of) local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric (as opposed to symbolic) data. The units operate only on their local data and on the inputs they receive via the connections. A neural network is a processing device, either an algorithm, or actual hardware, whose design was inspired by the design and functioning of animal brains and components thereof. Most neural networks have some sort of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples, just like children learn to recognise dogs from examples of dogs, and exhibit some structural capability for generalisation. Neurons are often elementary non-linear signal processors (in the limit they are simple threshold discriminators). Another feature of NNs which distinguishes them from other computing devices is a high degree of interconnection which allows a high degree of parallelism. Further, there is no idle memory containing data and programs, but rather each neuron is pre-programmed and continuously active. The term "neural net" should logically, but in common usage never does, also include biological neural networks, whose elementary structures are far more complicated than the mathematical models used for ANNs. See Aspirin, Hopfield network, McCulloch-Pitts neuron.