A convolutional neural network instruction data storage system and method

Abstract

The invention discloses a convolutional neural network instruction data storage system and method, and belongs to data processing of artificial intelligence, the technical problem to be solved by theinvention is how to efficiently, orderly and conveniently increase the number of model layers of the convolution neural network, data access with exponential growth in the number of convolution kernelweights. The technical scheme adopted is as follows: a convolutional neural network instruction data storage system is provided. The system includes a computing unit module, an input buffer module, an output buffer module, an output selection module, an instruction distribution module, a first data storage module, a second data storage module and a central control module; the central control module is respectively connected to and control the central control module, The calculation unit module, the input buffer module, the output buffer module, the output selection module, the instruction distribution module, the first data storage module and the second data storage module. The invention also discloses a convolutional neural network instruction data storage method.

Description

technical field [0001] The invention relates to the field of artificial intelligence data processing, in particular to a convolutional neural network instruction data storage system and method. Background technique [0002] Artificial neural network, referred to as neural network, is a mathematical model or computational model that imitates the structure and function of a biological neural network. As the most important branch of artificial neural network, convolutional neural network is an efficient recognition method that has been developed in recent years and has attracted widespread attention. In the 1960s, Hubel and Wiesel discovered that its unique network structure can effectively reduce the complexity of the feedback neural network when studying the neurons used for local sensitivity and direction selection in the cat's cerebral cortex, and then proposed the convolutional neural network. [0003] The basic structure of a general convolutional neural network includes...

AI Technical Summary

Problems solved by technology

However, this technology cannot achieve fast and efficient data storage control when the number of model layers of the convolutional neural network is greatly increased, and the number of convolution kernel weight values ​​increases exponentially.

Images