A computing method and device

Abstract

An operation method and device, the operation device includes an input module for inputting data; a model generation module for constructing a model according to the input data; a neural network operation module for generating and caching operation instructions based on the model, and Perform operations on the data to be processed to obtain operation results; the output module is used to output operation results. The device and method disclosed in the present disclosure can avoid the extra overhead caused by running the entire software architecture in the traditional method.

Description

technical field [0001] The disclosure belongs to the fields of computer architecture, deep learning and neural network, and more specifically relates to a computing method and device. Background technique [0002] Deep learning is a branch of machine learning that attempts to perform high-level abstractions on data using algorithms that contain complex structures or multiple processing layers consisting of multiple nonlinear transformations. [0003] Deep learning is a method based on representation learning of data in machine learning. Observations (such as an image) can be represented in a variety of ways, such as a vector of intensity values ​​for each pixel, or more abstractly as a series of edges, regions of a specific shape, etc. Whereas it is easier to learn tasks from examples (e.g., face recognition or facial expression recognition) using some specific representations. [0004] So far, several deep learning architectures, such as deep neural network, convolutional...

AI Technical Summary

Problems solved by technology

However, in some low-memory, real-time application scenarios, running the entire software architecture will consume too many computing resources

Images