Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
  • AI
  • Tech
  • Cybersecurity
  • Finance
  • DeFi & Blockchain
  • Startups
  • Gaming
Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

Microsoft Researchers’ Latest Computer Vision Algorithm Can Outperform Humans

byDataconomy News Desk
February 17, 2015
in Artificial Intelligence, News

Researchers at Microsoft in Beijing may have developed the first computer vision system that has surpassed human capabilities in classifying objects defined in the ImageNet 2012 classification dataset, according to recently-published paper.

“To our knowledge, our result is the first to surpass human-level performance…on this visual recognition challenge,” the paper says.

The deep learning based system – Parametric Rectified Linear Unit network – achieved a 4.94% test error rate as compared to Baidu’s systems’ 5.98% and the ILSVRC 2014 winner, GoogLeNet’s 6.66%. Human’s have an error rate of 5.1%.

Microsoft Researchers' Latest Computer Vision Algorithm Can Outperform Humans

The paper titled  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, the researchers point out that the experiments were carried out on the 1000-class ImageNet 2012 dataset which contains about 1.2 million training images, 50,000 validation images, and 100,000 test images with no published labels.

“While our algorithm produces a superior result on this particular dataset, this does not indicate that machine vision outperforms human vision on object recognition in general…On recognizing elementary object categories…machines still have obvious errors in cases that are trivial for humans. Nevertheless, we believe our results show the tremendous potential of machine algorithms to match human-level performance for many visual recognition tasks,” the paper’s authors clarify.

The paper has been co-written by Kaiming He, a researcher in Microsoft Research Asia’s Visual Computing Group,along with academic interns, Xiangyu Zhang and Shaoqing Ren, and principal researcher, Jian Sun of Microsoft Research.

Follow @DataconomyMedia

(Image credit: Mike Mozart, via Flickr)

Stay Ahead of the Curve!

Don't miss out on the latest insights, trends, and analysis in the world of data, technology, and startups. Subscribe to our newsletter and get exclusive content delivered straight to your inbox.

Tags: beijingChinaComputer Visionimage recognitionMicrosoftWeekly Newsletter

Related Posts

Verizon down: Latest Verizon outage map for service issues

Verizon down: Latest Verizon outage map for service issues

October 10, 2025
A critical Oracle zero-day flaw is being actively abused by hackers

A critical Oracle zero-day flaw is being actively abused by hackers

October 10, 2025
Microsoft Copilot can now create documents and search your Gmail

Microsoft Copilot can now create documents and search your Gmail

October 10, 2025
Google Messages is about to get a lot smarter with this AI tool

Google Messages is about to get a lot smarter with this AI tool

October 10, 2025
Here is how WhatsApp will let you display your Facebook account

Here is how WhatsApp will let you display your Facebook account

October 10, 2025
The Windows 10 doomsday clock is ticking for 500 million users

The Windows 10 doomsday clock is ticking for 500 million users

October 10, 2025
Please login to join discussion

LATEST NEWS

Verizon down: Latest Verizon outage map for service issues

A critical Oracle zero-day flaw is being actively abused by hackers

Microsoft Copilot can now create documents and search your Gmail

Google Messages is about to get a lot smarter with this AI tool

Here is how WhatsApp will let you display your Facebook account

The Windows 10 doomsday clock is ticking for 500 million users

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy

Follow Us

  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
No Result
View All Result
Subscribe

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy Policy.