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

Deep Neural Network Structure, Method of Using Deep Neural Network, and Readable Media

A deep neural network and network structure technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as increased waiting time

Active Publication Date: 2022-03-08
IND TECH RES INST
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although one can increase the network size (both depth and width) to achieve higher image recognition accuracy, the price of doing so is that the latency of forward inference will increase

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
  • Deep Neural Network Structure, Method of Using Deep Neural Network, and Readable Media
  • Deep Neural Network Structure, Method of Using Deep Neural Network, and Readable Media
  • Deep Neural Network Structure, Method of Using Deep Neural Network, and Readable Media

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present application will now be described in detail with reference to the accompanying drawings, wherein like reference numerals will be used to identify the same or similar elements throughout the several views. It should be noted that the drawings are to be viewed in the direction of orientation of the reference numbers.

[0036] In an embodiment of the present application, a deep neural network structure includes: a main path having, in sequential order, an input layer, only X groups of layers, at least one pooling layer, and a classification layer, the input layer for receiving media data, the group of only X by layers is used to extract features from the media data, the at least one pooling layer is used for the X by layers from the main path The output of the formed group is down-sampled, and the classification layer is used to calculate a class likelihood in each of the plurality of predetermined data classes when the media data traverses the main path, where...

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 present invention provides a deep neural network structure and method for improving the accuracy of identification and classification, and efficiently identifying and classifying multimedia data into one of a plurality of predetermined data categories. In a deep neural network, using side branches (or sub-side branches, sub-sub-side branches, etc.) The network has fast forward reasoning ability, thereby improving the recognition and classification accuracy and efficiency of the deep neural network.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS [0002] This non-provisional patent application claims priority under 35 U.S.C. §119(e) to U.S. Provisional Patent Application No. 62 / 538,811, filed July 31, 2017, which is incorporated herein in its entirety for reference. technical field [0003] The present application relates to a deep neural network (deep neural network, DNN). Background technique [0004] Neural networks are used in a variety of applications. For example, neural networks have been designed to extract features from data such as images, sound, video, text, or time series to identify patterns in the data. Neural networks are built as a pattern of collections of neurons connected into an acyclic graph. In other words, the output of some neurons can become the input of other neurons. Neural network models are often organized into distinct layers formed by neurons. Different layers can perform different kinds of transformations on their inputs. The signa...

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): G06V10/764G06V10/82G06V10/44G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06F18/214G06F18/24G06N3/08G06V10/454G06V10/82G06N3/045G06F18/24133G06V10/751G06N3/02G06T2207/10028G06F18/285
Inventor 黄茂裕赖璟皓
Owner IND TECH RES INST