Unlock instant, AI-driven research and patent intelligence for your innovation.

Computing system and computing method of deep neural network

A deep neural network and computing system technology, applied in neural learning methods, biological neural network models, marketing, etc., can solve problems such as high network communication overhead, low computing efficiency, and small network communication overhead, and achieve low computing efficiency , improve computing efficiency, and solve the effect of large network communication overhead

Active Publication Date: 2017-09-19
SHENZHEN TENCENT COMP SYST CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a deep neural network computing system and computing method with high computing efficiency and low network communication overhead; Expensive technical issues

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Computing system and computing method of deep neural network
  • Computing system and computing method of deep neural network
  • Computing system and computing method of deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Referring to the drawings, wherein like reference numerals represent like components, the principles of the present invention are exemplified when implemented in a suitable computing environment. The following description is based on illustrated specific embodiments of the invention, which should not be construed as limiting other specific embodiments of the invention not described in detail herein.

[0030] In the following description, specific embodiments of the present invention are described with reference to steps and symbols for operations performed by one or more computers, unless otherwise stated. Accordingly, it will be understood that the steps and operations, which at times are referred to as being performed by a computer, include manipulation by a computer processing unit of electronic signals representing data in a structured form. This manipulation transforms the data or maintains it at a location in the computer's memory system that can reconfigure or ot...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a deep neural network computing system, which includes a main server, multiple central parameter servers and multiple computing modules; wherein the computing modules include local parameter servers and multiple computing units. The present invention also provides a computing method for the computing system of the deep neural network. The computing system and computing method of the deep neural network of the present invention improve the computing efficiency of the computing system and reduce the network complexity of the computing system by setting a local parameter server. communication overhead.

Description

technical field [0001] The invention relates to the field of computing structures, in particular to a computing system and a computing method of a deep neural network. Background technique [0002] At present, when advertisements are placed in the industry, a method based on an estimation of advertisement click rate is widely used to rank advertisements. The specific method is to first estimate the click-through rate of the candidate advertisement through the deep neural network, that is, the predicted click-through rate of the advertisement (pCTR, predicted click-through rate), then calculate the quality of the advertisement based on pCTR, and finally calculate the advertisement according to Bid (Bid)*Quality is displayed in reverse order, and the higher the bid and the higher the quality of the advertisement, the higher the ranking. The ranking follows the Generalized Second Price Auction (GSP, Generalized Second Price Auction) mechanism, which can maximize the revenue of...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q30/02G06N3/08
Inventor 李毅邹永强金涬郭志懋
Owner SHENZHEN TENCENT COMP SYST CO LTD