Stories
Slash Boxes
Comments

SoylentNews is people

posted by cmn32480 on Saturday May 16 2015, @10:45PM   Printer-friendly
from the tin-foil-face-mask-time dept.

Using the ImageNet object classification benchmark, Baidu’s Minwa supercomputer scanned more than 1 million images and taught itself to sort them into about 1000 categories and achieved an image identification error rate of just 4.58 percent, beating humans, Microsoft and Google. Baidu's Minwa scored 95.42%, Google's system scored a 95.2%, and Microsoft's, a 95.06%, Baidu said.

“Our company is now leading the race in computer intelligence,” said Ren Wu, a Baidu scientist working on the project. “I think this is the fastest supercomputer dedicated to deep learning,” he said. “We have great power in our hands—much greater than our competitors.

A paper released Monday [May 11, 2015] is intended to provide a taste of what Minwa’s extra oomph can do. It describes how the supercomputer was used to train a neural network that set a new record on a standard benchmark for image-recognition software. The ImageNet Classification Challenge, as it is called, involves training software on a collection of 1.5 million labeled images in 1,000 different categories, and then asking that software to use what it learned to label 100,000 images it has not seen before.

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 0, Informative) by Anonymous Coward on Sunday May 17 2015, @12:34AM

    by Anonymous Coward on Sunday May 17 2015, @12:34AM (#183879)

    It a nigga, ha ha ha, it a nigga, ha ha ha.

    Starting Score:    0  points
    Moderation   0  
       Troll=1, Informative=1, Total=2
    Extra 'Informative' Modifier   0  

    Total Score:   0  
  • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:13AM

    by Anonymous Coward on Sunday May 17 2015, @01:13AM (#183890)

    That's double racist.

    • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:20AM

      by Anonymous Coward on Sunday May 17 2015, @01:20AM (#183892)

      Oh yeah things were so much better back in the old days when Asians were banned from appearing in films and Mickey Rooney was all yellowfaced. Ah so! Only single racist!

      • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:24AM

        by Anonymous Coward on Sunday May 17 2015, @01:24AM (#183894)

        The best racist is zero racist.

        • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:27AM

          by Anonymous Coward on Sunday May 17 2015, @01:27AM (#183896)

          All races are crap! Especially yours!

          • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:33AM

            by Anonymous Coward on Sunday May 17 2015, @01:33AM (#183899)

            No, all races are good. All humans are equal.

            • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:41AM

              by Anonymous Coward on Sunday May 17 2015, @01:41AM (#183903)

              All humans are equally full of shit, particularly when constipated.

              • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @01:43AM

                by Anonymous Coward on Sunday May 17 2015, @01:43AM (#183905)

                Defecation has nothing to do with skin color. We all have the same intestines. We all have the same colons. We all have equal colons.

                • (Score: 0) by Anonymous Coward on Sunday May 17 2015, @02:21PM

                  by Anonymous Coward on Sunday May 17 2015, @02:21PM (#184043)

                  As with all things, some people's colons are more equal than others [nickpaffett.com].

        • (Score: 2) by maxwell demon on Sunday May 17 2015, @07:30AM

          by maxwell demon (1608) on Sunday May 17 2015, @07:30AM (#183981) Journal

          Surely −1 racists is better, since −1 < 0, right? :-)

          --
          The Tao of math: The numbers you can count are not the real numbers.