Apparatus and method for realizing accelerator of sparse convolutional neural network

Abstract

The invention provides an apparatus and method for realizing an accelerator of a sparse convolutional neural network. According to the invention, the apparatus herein includes a convolutional and pooling unit, a full connection unit and a control unit. The method includes the following steps: on the basis of control information, reading convolutional parameter information, and input data and intermediate computing data, and reading full connected layer weight matrix position information, in accordance with the convolutional parameter information, conducting convolution and pooling on the input data with first iteration times, then on the basis of the full connected layer weight matrix position information, conducting full connection computing with second iteration times. Each input data is divided into a plurality of sub-blocks, and the convolutional and pooling unit and the full connection unit separately operate on the plurality of sub-blocks in parallel. According to the invention, the apparatus herein uses a specific circuit, supports a full connected layer sparse convolutional neural network, uses parallel ping-pang buffer design and assembly line design, effectively balances I / O broadband and computing efficiency, and acquires better performance power consumption ratio.

Description

technical field [0001] The present invention relates to artificial neural networks, and more particularly to devices and methods for implementing sparse convolutional neural network accelerators. Background technique [0002] Artificial Neural Networks (ANN), also referred to as Neural Network (NN), is an algorithmic mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing. In recent years, neural networks have developed rapidly and are widely used in many fields, including image recognition, speech recognition, natural language processing, weather forecast, gene expression, content push and so on. [0003] figure 1 Diagram illustrating the computational schematic of a neuron in an artificial neural network. [0004] The accumulated stimulus of a neuron is the sum of the stimulus delivered by other neurons and the corresponding weight. Xj is used to represent the accumulation of the j...

AI Technical Summary

Problems solved by technology

However, the fully connected layer still has a large number of parameters. If the fully connected layer is sparsely processed, the amount of calculation will be greatly reduced.

Images