Device and method for rarefaction of neural network layer, and storage medium

Abstract

The invention relates to a device, a board card, a method and a readable storage medium for rarefaction of a neural network layer, in which a computing device of the present disclosure is included in an integrated circuit device including a universal interconnection interface and other processing devices. And the computing device interacts with other processing devices to jointly complete the computing operation specified by the user. The integrated circuit device can further comprise a storage device, and the storage device is connected with the computing device and the other processing devices and used for data storage of the computing device and the other processing devices.

Description

technical field [0001] The present disclosure relates generally to the field of neural networks. More specifically, the present disclosure relates to a device, a board, a method and a readable storage medium for sparsifying a neural network layer. Background technique [0002] In recent years, with the rapid development of deep learning, the performance of algorithms in a series of fields such as computer vision and natural language processing has made leaps and bounds. However, the deep learning algorithm is a computing-intensive and storage-intensive tool. With the increasing complexity of information processing tasks, the requirements for real-time and accuracy of the algorithm continue to increase, and the neural network is often designed deeper and deeper, making Its computing power and storage space requirements are increasing, making it difficult for existing artificial intelligence technology based on deep learning to be directly applied to mobile phones, satellites...

AI Technical Summary

Problems solved by technology

Although the existing fine-grained parameter sparse method model performs well, it is not friendly to hardware memory access, that is, the on-chip and off-chip input / output overhead is large, and the performance is low; on the other hand, the structured sparse method based on channels and convolution kernels Although the method improves the hardware performance, the loss of model accuracy is large; finally, most of the existing sparse algorithms are offline fine-tuning, that is, the pre-training model is sparse and then fine-tuned. The offline fine-tuning method has many restrictions and cannot be used in model training There are more substantial performance gains

Images