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

Sparse convolutional neural network

A convolutional neural network, sparse technology, applied in the field of sparse convolutional neural network, can solve problems such as a large amount of computing resources and large energy consumption

Pending Publication Date: 2020-12-18
MICROSOFT TECH LICENSING LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Performing inference on these very large models often requires large computational resources and consumes a large amount of energy

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
  • Sparse convolutional neural network
  • Sparse convolutional neural network
  • Sparse convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present disclosure will now be discussed with reference to several example implementations. It should be understood that these implementations are discussed only to enable those of ordinary skill in the art to better understand and thus enable the present disclosure, and not to imply any limitation on the scope of the subject matter.

[0012] As used herein, the term "comprising" and variations thereof are to be read as open-ended terms meaning "including but not limited to". The term "based on" is to be read as "based at least in part on". The terms "an implementation" and "an implementation" are to be read as "at least one implementation". The term "another implementation" is to be read as "at least one other implementation". The terms "first", "second", etc. may refer to different or the same object. Other definitions, both express and implied, may also be included below.

[0013] The basic principles and several example implementations of the present disclos...

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

Various implementations of the present disclosure relate to sparse convolutional neural networks. In some implementations, a computer-implemented method includes steps of quantizing an input feature map to obtain a quantized input feature map; determining a sparse mask for an output feature map through a quantized version of a convolutional neural network based on the quantized input feature map,with the sparse mask indicating a position of a non-zero term in the output feature map; based on the input feature map, determining a non-zero term indicated by the sparse mask in the output featuremap by the convolutional neural network.

Description

Background technique [0001] At present, many major advances in artificial intelligence come from convolutional neural networks (CNN) with great depth. Performing inference on these very large models typically requires significant computational resources and consumes a large amount of energy. Therefore, how to implement these models in a low-computational-cost and energy-efficient manner is an open problem. Contents of the invention [0002] According to some implementations of the present disclosure, a scheme for reducing the overhead of a convolutional neural network through quantization and sparse convolution is provided. For example, the input feature map can be quantized to obtain a quantized input feature map. Based on the quantized input feature map, a sparse mask for the output feature map is determined by a quantized version of the convolutional neural network, the binary sparse mask indicating the location of non-zero entries in the output feature map. Based on t...

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 Applications(China)
IPC IPC(8): G06N3/04G06K9/62
CPCG06N3/045G06F18/2136G06F18/241G06N3/10G06N3/048G06F5/01G06F17/15
Inventor 张宸刘云新
Owner MICROSOFT TECH LICENSING LLC