Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Systems and methods for neural architecture search

A neural and neural network technology, applied in the field of neural architecture search, which can solve problems such as differences

Pending Publication Date: 2020-04-03
SWISSCOM AG
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition to improving the efficiency of training neural networks, the ability to choose an appropriate neuron structure may make the difference between providing a neural network that can solve a technical problem and one that does not

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
  • Systems and methods for neural architecture search
  • Systems and methods for neural architecture search
  • Systems and methods for neural architecture search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Embodiments of the present disclosure relate to systems and methods for neural architecture search. When faced with the task of having to provide a neural network for performing a selected task, neural architecture search is used to identify a preferred model for such a neural network. A preferred model can be identified based on an analysis of multiple candidate models. Identifying the preferred model involves providing a computational graph consisting of multiple distinct nodes connected by multiple edges. A computation graph can be thought of as providing multiple subgraphs (subgraphs can be thought of as "candidate models"). Each subgraph is a selection of some nodes and edges in the computational graph.

[0053] A computational graph includes a number of weights that scale information as it flows through the network (e.g., between different nodes). Weights may be applied between nodes such that items of input data received at a node may be scaled based on the pr...

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

A computer-implemented method of neural architecture search is disclosed. Embodiments may provide a neural network (100) configured to perform a selected task. A computational graph (200) is obtainedwhich includes a plurality of nodes, edges and weightings associated with the nodes / edges. The computational graph (200) includes a plurality of candidate models in the form of subgraphs (301,302) ofthe computational graph (200). Selected subgraphs are trained sequentially, with the weightings corresponding to each said subgraph being updated in response to training. For each weighting in a subgraph which is shared with another subgraph, updates to the weightings (in response to training that subgraph) are controlled based on an indication of how important to the another subgraph a node / edgeassociated with that weighting is.

Description

technical field [0001] The present disclosure relates to the field of neural architecture search. In particular, the present disclosure relates to systems and methods for designing neural networks. Background technique [0002] By providing enhanced computing power and access to increasing amounts of suitable training data, machine learning techniques have been increasingly used to provide improved solutions to many technical problems. In particular, the use of neural networks has become increasingly common as a means of providing concise and effective solutions to many of these technical problems. [0003] A neural network typically has a structure comprising many interconnected neurons. Each neuron in the network is arranged to receive input data, which the neuron scales and performs a function on before providing some output data. This output data can then be fed into subsequent neurons as input data for subsequent neurons. These subsequent neurons can then likewise s...

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): G06N3/08G06N3/10
CPCG06N3/08G06N3/084G06N3/105G06N3/048G06N3/045G06N3/044G06N3/006G06N3/082G06N3/086G06F40/20G06F18/24
Inventor 亚辛·贝尼亚希亚卡米尔本纳尼·斯密雷斯迈克尔·贝瑞斯维尔克劳迪乌·姆萨特
Owner SWISSCOM AG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com