Selecting a neural network architecture for a supervised machine learning problem

A machine learning and neural network technology, applied in neural architecture, biological neural network models, neural learning methods, etc.

Pending Publication Date: 2021-03-09
MICROSOFT TECH LICENSING LLC
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In particular, the present disclosure is directed to systems and methods for selecting a neural network architecture for solving a machine learning problem in a given machine learning problem space

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
  • Selecting a neural network architecture for a supervised machine learning problem
  • Selecting a neural network architecture for a supervised machine learning problem
  • Selecting a neural network architecture for a supervised machine learning problem

Examples

Experimental program
Comparison scheme
Effect test

example 9

[0108] Example 9 is a non-transitory machine-readable medium storing instructions that cause one or more machines to perform operations including: accessing a machine learning problem space associated with a machine learning problem and for solving the a plurality of untrained candidate neural networks for the machine learning problem; for each untrained candidate neural network, computing at least one expressiveness metric that captures the expressiveness of the candidate neural network with respect to the machine learning problem; for For each untrained candidate neural network, computing at least one trainability metric that captures the trainability of the candidate neural network with respect to the machine learning problem; based on the at least one expressiveness metric and the at least one trainability A performance metric selects at least one candidate neural network for solving the machine learning problem; and provides an output representative of the selected at leas...

example 15

[0114] Example 15 is a method comprising: accessing a machine learning problem space of quantities associated with a machine learning problem and a plurality of untrained candidate neural networks for solving the machine learning problem; for each untrained for the candidate neural network, computing at least one expressiveness metric capturing the expressiveness of the candidate neural network with respect to the machine learning problem; for each untrained candidate neural network, computing the learning at least one trainability measure of the trainability of a problem; selecting at least one candidate neural network for solving the machine learning problem based on the at least one expressiveness measure and the at least one trainability measure; and providing a representation The output of the selected at least one candidate neural network.

[0115] In Example 16, the subject matter of Example 15 includes wherein the at least one expressiveness metric represents a measure...

example 21

[0120] Example 21 is at least one machine-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform the method for implementing any of Examples 1-20. operate.

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

Systems and methods for selecting a neural network for a machine learning problem are disclosed. A method includes accessing an input matrix. The method includes accessing a machine learning problem space associated with a machine learning problem and multiple untrained candidate neural networks for solving the machine learning problem. The method includes computing, for each untrained candidate neural network, at least one expressivity measure capturing an expressivity of the candidate neural network with respect to the machine learning problem. The method includes computing, for each untrained candidate neural network, at least one trainability measure capturing a trainability of the candidate neural network with respect to the machine learning problem. The method includes selecting, based on the at least one expressivity measure and the at least one trainability measure, at least one candidate neural network for solving the machine learning problem.

Description

Background technique [0001] Many different types of neural network architectures are known (eg, convolutional neural networks, feed-forward neural networks, etc.). Choosing a neural network architecture (and sub-architectures within a given architecture type) to solve a given machine learning problem can be challenging. Description of drawings [0002] In the figures of the drawings, some embodiments of the present technology are shown by way of example and not limitation. [0003] figure 1 Illustrated is an example system in which selecting a neural network architecture for solving a machine learning problem may be implemented in accordance with some embodiments. [0004] figure 2 A flowchart illustrating an example method for selecting a neural network architecture for solving a machine learning problem according to some embodiments. [0005] image 3 A flowchart illustrating an example method for reducing error rates according to some embodiments is shown. [0006]...

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): G06N3/04G06N3/08G06N5/00
CPCG06N3/08G06N20/10G06N5/01G06N3/047G06N3/045G06N3/044
Inventor S·阿米扎德杨格N·富西F·P·卡萨莱
Owner MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap