Neural network computing apparatus and system, and method therefor

Abstract

In order to provide a neural network computing apparatus and system, as well as a method therefor, which operate via a synchronization circuit in which all components are synchronized with one system clock, and which include a dispersion-type memory structure for storing artificial neural network data, and a calculating structure for processing all neurons through time-sharing in a pipeline circuit, the present invention comprises: a control unit for controlling the neural network computing apparatus; a plurality of memory units for outputting both a connecting line attribute value and a neuron attribute value; and one calculating unit for using the connecting line attribute value and neuron attribute value inputted from the plurality of memory units so as to calculate a new neuron attribute value and provide feedback to each of the plurality of memory units.

Description

technical field

[0001] Exemplary embodiments of the present invention relate to digital neural network computing technology; in particular, to a neural network computing device and method thereof, all components of the device operate as circuits synchronized with a system clock, and the device includes a A distributed memory structure for storing data of an artificial neural network and a computational structure for processing all neurons in a time-division manner through pipelined circuits. Background technique

[0002] A digital neural network computer is an electronic circuit that simulates a biological neural network in order to construct a function similar to that of the brain.

[0003] In order to artificially realize the biological neural network, various calculation methods with a structure similar to the biological neural network have been proposed, and the construction method of the biological neural network can be called a neural network model. In most neural net...

Images