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

Quantum deep learning

A quantum and qubit technology, applied in the field of training Boltzmann machines, can solve problems such as high cost, reduced model quality, and inability to train graphics at one time

Inactive Publication Date: 2017-08-01
MICROSOFT TECH LICENSING LLC
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The contrastive divergence approximation is inappropriate in some applications, and in any case, methods based on contrastive divergence cannot train the entire graph at once and instead rely on training the system one layer at a time, which is costly and reduces the quality of the model
Finally, more coarse approximations are needed to train a full Boltzmann machine, which potentially has connections between all hidden and visible units and can limit the quality of the optimum found in the learning algorithm

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
  • Quantum deep learning
  • Quantum deep learning
  • Quantum deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] As used in this application and in the claims, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. Additionally, the term "include" means "comprise". Furthermore, the term "coupled" does not exclude the presence of intermediate elements between the coupled items.

[0018] The systems, devices and methods described herein should not be construed as limiting in any way. Instead, the present disclosure relates to all novel and non-obvious features and aspects of the various disclosed embodiments both alone and in various combinations and subcombinations with each other. The disclosed systems, methods and apparatus are not limited to any specific aspect or feature or combination thereof, nor do the disclosed systems, methods and apparatus claim to present any one or more specific advantages or solve any one or more specific problems. Any theory of operation is to support the illustration, but the disclosed systems...

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

Boltzmann machines are trained using an objective function that is evaluated by sampling quantum states that approximate a Gibbs state. Classical processing is used to produce the objective function, and the approximate Gibbs state is based on weights and biases that are refined using the sample results. In some examples, amplitude estimation is used. A combined classical / quantum computer produces suitable weights and biases for classification of shapes and other applications.

Description

technical field [0001] This disclosure relates to the use of quantum computers to train Boltzmann machines. Background technique [0002] Deep learning is a relatively new paradigm for machine learning that has dramatically impacted the way classification, inference, and artificial intelligence (AI) tasks are performed. Deep learning began with the suggestion that in order to perform complex AI tasks such as vision or language, it might be necessary to work on abstractions of initial data rather than raw data. For example an inference engine trained to detect cars may first take a raw image and first decompose it into simple shapes. Those shapes can form the first level of abstraction. These element shapes can then be grouped together into higher level abstract objects such as shock absorbers or wheels. The problem of determining whether a particular image is a car is then performed on abstract data rather than raw pixel data. In general, this process may involve many le...

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): G06N99/00
CPCG06N10/00G06N3/044G06N3/047G06N10/60D02G1/10D02G1/008A01D5/00G06N3/08
Inventor N·维贝K·斯沃雷A·卡珀尔
Owner MICROSOFT TECH LICENSING LLC