Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. Other Discussions
  3. The Insider News
  4. New method allows AI to learn indefinitely

New method allows AI to learn indefinitely

Scheduled Pinned Locked Moved The Insider News
htmlcomcollaborationannouncementlearning
5 Posts 3 Posters 0 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • K Offline
    K Offline
    Kent Sharkey
    wrote on last edited by
    #1

    Tech Xplore[^]:

    A team of AI researchers and computer scientists at the University of Alberta has found that current artificial networks used with deep-learning systems lose their ability to learn during extended training on new data.

    "Skynet begins to learn at a geometric rate."

    But it's from Alberta, so nothing to fear there. Unless there's oil involved.

    J N 3 Replies Last reply
    0
    • K Kent Sharkey

      Tech Xplore[^]:

      A team of AI researchers and computer scientists at the University of Alberta has found that current artificial networks used with deep-learning systems lose their ability to learn during extended training on new data.

      "Skynet begins to learn at a geometric rate."

      But it's from Alberta, so nothing to fear there. Unless there's oil involved.

      J Offline
      J Offline
      jochance
      wrote on last edited by
      #2

      Canadian Bacon (1995)[^]

      K 1 Reply Last reply
      0
      • J jochance

        Canadian Bacon (1995)[^]

        K Offline
        K Offline
        Kent Sharkey
        wrote on last edited by
        #3

        Definitely an underrated movie. :thumbsup:

        TTFN - Kent

        1 Reply Last reply
        0
        • K Kent Sharkey

          Tech Xplore[^]:

          A team of AI researchers and computer scientists at the University of Alberta has found that current artificial networks used with deep-learning systems lose their ability to learn during extended training on new data.

          "Skynet begins to learn at a geometric rate."

          But it's from Alberta, so nothing to fear there. Unless there's oil involved.

          J Offline
          J Offline
          jochance
          wrote on last edited by
          #4

          Quote:

          They also are unable to grow any more intelligent by training on new datasets.

          That stood out to me as wrong at first. Reading on, I realized you see that exact catastrophic forgetting with image generation tools and new models. That this seems to boil down to a git commit message of "initialize the variables between runs" is interesting. Sounds solid too.

          1 Reply Last reply
          0
          • K Kent Sharkey

            Tech Xplore[^]:

            A team of AI researchers and computer scientists at the University of Alberta has found that current artificial networks used with deep-learning systems lose their ability to learn during extended training on new data.

            "Skynet begins to learn at a geometric rate."

            But it's from Alberta, so nothing to fear there. Unless there's oil involved.

            N Offline
            N Offline
            Nelek
            wrote on last edited by
            #5

            Quote:

            New method allows AI to learn indefinitely

            Did they tried to make it forget? I know a lot of students that do it too :-D

            M.D.V. ;) If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about? Help me to understand what I'm saying, and I'll explain it better to you Rating helpful answers is nice, but saying thanks can be even nicer.

            1 Reply Last reply
            0
            Reply
            • Reply as topic
            Log in to reply
            • Oldest to Newest
            • Newest to Oldest
            • Most Votes


            • Login

            • Don't have an account? Register

            • Login or register to search.
            • First post
              Last post
            0
            • Categories
            • Recent
            • Tags
            • Popular
            • World
            • Users
            • Groups