Artificial neural network operation circuit

Abstract

The invention discloses an artificial neural network operation circuit. The artificial neural network operation circuit comprises a controller and at least one neuron, wherein the controller is used for sending a control instruction and learning parameters to the at least one neuron; and the at least one neuron is connected with the controller and used for performing neuron operation on input dataaccording to the control instruction and the learning parameters and outputting an operation result. The artificial neural network operation circuit solves a technical problem that a CPU (Central Processing Unit) is low in operation efficient for an artificial neural network.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an artificial neural network operation circuit. Background technique [0002] Artificial Neural Network (Artificial Neural Network) is a research hotspot in the field of artificial intelligence since the 1980s. It abstracts the brain neuron network from the perspective of biological information processing, and forms different networks according to different connection methods. The unique nonlinear adaptive information processing ability of artificial neural network overcomes the shortcomings of traditional artificial intelligence methods for intuition, such as patterns, speech recognition, and unstructured information processing, making it useful in pattern recognition, intelligent control, optimal combination, It has been successfully applied in forecasting and other fields. [0003] However, the artificial neural network is a parallel distributed system. Traditional CPUs and GP...

AI Technical Summary

Problems solved by technology

[0005] An embodiment of the present invention provides an artificial neural network computing circuit to at least solve the technical problem of low CPU efficiency for artificial neural network computing

Images