Dataconomy
  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
Subscribe
No Result
View All Result
Dataconomy
  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

Microsoft Researchers’ Latest Computer Vision Algorithm Can Outperform Humans

by Dataconomy News Desk
February 17, 2015
in Machine Learning, News
Home Topics Data Science Machine Learning
Share on FacebookShare on TwitterShare on LinkedInShare on WhatsAppShare on e-mail

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)

Tags: beijingChinaComputer Visionimage recognitionMicrosoftWeekly Newsletter

Related Posts

Here is why people tape their phones on ceilings all over the world

Here is why people tape their phones on ceilings all over the world

December 1, 2023
Privacy on a new level with WhatsApp Secret Code

Privacy on a new level with WhatsApp Secret Code

December 1, 2023
ChatGPT turns 1 year old: Here is a brief recap of its infancy

ChatGPT turns 1 year old: Here is a brief recap of its infancy

November 30, 2023
Wrapped 2023: Is your average Spotify listening time high or low?

Wrapped 2023: Is your average Spotify listening time high or low?

November 30, 2023
AWS re:Invent 2023: Amazon raises the bar

AWS re:Invent 2023: Amazon raises the bar

November 30, 2023
Spotify Wrapped 2023 is here: How to check it out

Spotify Wrapped 2023 is here: How to check it out

November 29, 2023

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

LATEST ARTICLES

Hack your income: Unconventional ways you can earn free PayPal money online

The Rise of DAOs: Transforming governance through Ethereum’s decentralized autonomous organizations

Quizbot.ai: Artificial teacher, real success

Here is why people tape their phones on ceilings all over the world

Privacy on a new level with WhatsApp Secret Code

ChatGPT turns 1 year old: Here is a brief recap of its infancy

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy
  • Partnership
  • Writers wanted

Follow Us

  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
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.