• About Us
  • Contact Us
  • Cookie policy (EU)
  • Home
  • Privacy Policy
  • Video
  • Write for us
Today Headline
  • HOME
  • NEWS
    • POLITICS
    • News for today
    • Borisov news
  • FINANCE
    • Business
    • Insurance
  • Video
  • TECHNOLOGY
  • ENTERPRISE
  • LIFESTYLE
    • TRAVEL
    • HEALTH
    • ENTERTAINMENT
  • AUTOMOTIVE
  • SPORTS
  • Travel and Tourism
  • HOME
  • NEWS
    • POLITICS
    • News for today
    • Borisov news
  • FINANCE
    • Business
    • Insurance
  • Video
  • TECHNOLOGY
  • ENTERPRISE
  • LIFESTYLE
    • TRAVEL
    • HEALTH
    • ENTERTAINMENT
  • AUTOMOTIVE
  • SPORTS
  • Travel and Tourism
No Result
View All Result
TodayHeadline
No Result
View All Result

Physical systems perform machine-learning computations

January 27, 2022
in Technology
0
Physical systems perform machine-learning computations
0
SHARES
1
VIEWS
Share on FacebookShare on Twitter


Physical systems perform machine-learning computations

Cornell researchers have successfully trained (from left to right) a computer speaker, a simple electronic circuit and a laser to perform machine-learning computations. Credit: Logan G. Wright et al / Cornell University

You may not be able to teach an old dog new tricks, but Cornell researchers have found a way to train physical systems, ranging from computer speakers and lasers to simple electronic circuits, to perform machine-learning computations, such as identifying handwritten numbers and spoken vowel sounds.

The experiment is no mere stunt or parlor trick. By turning these physical systems into the same kind of neural networks that drive services like Google Translate and online searches, the researchers have demonstrated an early but viable alternative to conventional electronic processors—one with the potential to be orders of magnitude faster and more energy efficient than the power-gobbling chips in data centers and server farms that support many artificial-intelligence applications.

“Many different physical systems have enough complexity in them that they can perform a large range of computations,” said Peter McMahon, assistant professor of applied and engineering physics in the College of Engineering, who led the project. “The systems we performed our demonstrations with look nothing like each other, and they seem to [be] having nothing to do with handwritten-digit recognition or vowel classification, and yet you can train them to do it.”

The team’s paper, “Deep Physical Neural Networks Trained with Backpropagation,” published Jan. 26 in Nature. The paper’s co-lead authors are Logan Wright and Tatsuhiro Onodera, NTT Research postdoctoral fellows in McMahon’s lab.

The central research theme of McMahon’s group exists at the intersection of physics and computation: How to harness physical systems to perform computation more efficiently or faster than conventional computers.

For this project, they focused on one type of computation: Machine learning. The goal was to find out how to use different physical systems to perform machine learning in a generic way that could be applied to any system. The researchers developed a training procedure that enabled demonstrations with three diverse types of physical systems—mechanical, optical and electrical. All it required was a bit of tweaking, and a suspension of disbelief.

“Artificial neural networks work mathematically by applying a series of parameterized functions to input data. The dynamics of a physical system can also be thought of as applying a function to data input to that physical system,” McMahon said. “This mathematical connection between neural networks and physics is, in some sense, what makes our approach possible, even though the notion of making neural networks out of unusual physical systems might at first sound really ridiculous.”

For the mechanical system, the researchers placed a titanium plate atop a commercially available speaker, creating what is known in physics as a driven multimode mechanical oscillator. The optical system consisted of a laser beamed through a nonlinear crystal that converted the colors of incoming light into new colors by combining pairs of photons. The third experiment used a small electronic circuit with just four components—a resistor, a capacitor, an inductor and a transistor—of the sort a middle-school student might assemble in science class.

In each experiment, the pixels of an image of a handwritten number were encoded in a pulse of light or an electrical voltage that was fed into the system. The system processed the information and gave its output in a similar type of optical pulse or voltage. Crucially, for the systems to perform the appropriate processing, they had to be trained. So the researchers changed specific input parameters and ran multiple samples—such as different numbers in different handwriting—through the physical system, then used a laptop computer to determine how the parameters should be adjusted to achieve the greatest accuracy for the task. This hybrid approach leveraged the standard training algorithm from conventional artificial neural networks, called backpropagation, in a way that is resilient to noise and experimental imperfections.

The researchers were able to train the optical system to classify handwritten numbers with an accuracy of 97%. While this accuracy is below the state-of-the-art for conventional neural networks running on a standard electronic processor, the experiment shows that even a very simple physical system, with no obvious connection to conventional neural networks, can be taught to perform machine learning and could potentially do so much faster, and using far less power, than conventional electronic neural networks.

The optical system was also successfully trained to recognize spoken vowel sounds.

The researchers have posted their Physics-Aware-Training code online so that others can turn their own physical systems into neural networks. The training algorithm is generic enough that it can be applied to almost any such system, even fluids or exotic materials, and diverse systems can be chained together to harness the most useful processing capabilities of each one.

“It turns out you can turn pretty much any physical system into a neural network,” McMahon said. “However, not every physical system will be a good neural network for every task, so there is an important question of what physical systems work best for important machine-learning tasks. But now there is a way to try find out—which is what my lab is currently pursuing.”

Co-authors include doctoral student Martin Stein, Mong Postdoctoral Fellow Tianyu Wang, Darren Schachter, and Zoey Hu.


Harnessing noise in optical computing for AI


More information:
Logan G. Wright et al, Deep physical neural networks trained with backpropagation, Nature (2022). DOI: 10.1038 / s41586-021-04223-6

Provided by
Cornell University

Citation:
Physical systems perform machine-learning computations (2022, January 26)
retrieved 26 January 2022
from https://techxplore.com/news/2022-01-physical-machine-learning.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.

Tags: computationsmachinelearningperformphysicalSystems
Previous Post

Could the ‘Mono’ Virus Help Trigger Multiple Sclerosis?

Next Post

Nurse in Florida tragically dies 12 hours after testing positive for covid

Related Posts

Supernumerary virtual robotic arms can feel like part of the body
Technology

Supernumerary virtual robotic arms can feel like part of the body

In this diagram of the...

Read more
Researchers use GPUs to evaluate human brain connectivity
Technology

Researchers use GPUs to evaluate human brain connectivity

The image shows the superior...

Read more
Technology

Iplicit launches new board and announces senior appointments

The award-winning accounting software developer,...

Read more
Technology

Reuters reveals Musk seeks to put in less money in new Twitter deal financing

Business & FinanceDealsHuman InterestTechnology02 May...

Read more
Technology

Research allows for 3D printing of ‘organic electronics’

An example of 3D laser...

Read more
Load More
Next Post

Nurse in Florida tragically dies 12 hours after testing positive for covid

  • Trending
  • Comments
  • Latest

Ardeer Thistle: Hugh Clarke of Clarke ePOS UK to take over

Dog Waited Seven Days At Side Of Road Because His Owner Said ‘Stay’

Dog Waited Seven Days At Side Of Road Because His Owner Said ‘Stay’

Classic Macaroni Salad (quick and creamy)

Classic Macaroni Salad (quick and creamy)

Horror as goat gives birth to ‘humanoid kid’ with baby-like face

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Brose names new operations chief

Brose names new operations chief

Island-hopping in Greece for £78 a night on a bargain Celestyal all-inclusive cruise

Island-hopping in Greece for £78 a night on a bargain Celestyal all-inclusive cruise

About Us

Todayheadline the independent news and topics discovery
A home-grown and independent news and topic aggregation . displays breaking news linking to news websites all around the world.

Follow Us

Latest News

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Boris Johnson latest news: PM under fire over Chris Pincher’s appointment amid mounting allegations

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Jan. 6 Live: Trump Demanded to Be Taken to Capitol on January 6: Secret Service Sources

Brose names new operations chief

Brose names new operations chief

  • Real Estate
  • Education
  • Parenting
  • Cooking
  • NFL Games On TV Today
  • Travel and Tourism
  • Home & Garden
  • Pets
  • Privacy & Policy
  • Contact
  • About

© 2021 All rights are reserved Todayheadline

No Result
View All Result
  • Real Estate
  • Education
  • Parenting
  • Cooking
  • NFL Games On TV Today
  • Travel and Tourism
  • Home & Garden
  • Pets
  • Privacy & Policy
  • Contact
  • About

© 2021 All rights are reserved Todayheadline

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In

Add New Playlist

Posting....