You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please, join our community today!

Results 1 to 3 of 3

Thread: Intel Releases Neuromorphic Chip at CES

  1. #1
    Join Date
    Apr 2013
    East SF Bay Area
    Thumbs Up
    Received: 437
    Given: 406

    Intel Releases Neuromorphic Chip at CES

    Intel is in a race to stay relevant with a chip that works by reproducing how the human brain works with neural networks. They also announced a new quantum chip at the CES that is to be on a par with the IBM 50 qubit chip from IBM. I wish both these companies success for the more competition there is the better, for it will drive down cost and increase availability in these two areas which represent a path to the future. The wider and broader the technology revolution the better for everyone, concentration and wealth and power rarely are broadly beneficial. The less losers and the more winners a society has the better.

    This is just another step in the race for AI/ML that is accelerating at an ever increasing rate along with the programing to support it. This is the greatest race of any type in the history of man with ramifications and results that will stun and surprise us all. I just hope the surprises are pleasant for if mishandled could become the ultimate nightmare for many. My main concern is that AI could greatly concentrate wealth, power and control instead of advancing the well being of all. Great power requires great wisdom and this will be the greatest power of all.

    0 Not allowed!
    Last edited by Arthur Hanson; 01-09-2018 at 07:18 PM.

  2. #2
    Blogger Bernard Murphy's Avatar
    Join Date
    Aug 2015
    California Gold Country
    Thumbs Up
    Received: 307
    Given: 377
    Interesting. I looked around and can't find much substance beyond the usual marketing hype, other than it seems to be based on an RNN. Anyone else able to find more detail?

    0 Not allowed!

  3. #3
    Top Influencer
    Join Date
    Oct 2015
    Thumbs Up
    Received: 182
    Given: 21
    My best guess is it implements the memory cells used in RNNs in silicon. There are many other chip startups doing similar things, but competition is good.

    1 Not allowed!

Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts