back to article MIT boffins cram ML training into microcontroller memory

Researchers claim to have developed techniques to enable the training of a machine learning model using less than a quarter of a megabyte of memory, making it suitable for operation in microcontrollers and other edge hardware with limited resources. The researchers at MIT and the MIT-IBM Watson AI Lab say they have found " …

  1. Anonymous Coward
    Anonymous Coward

    Why the focus on microcontrollers?

    If it is true these algorithmic improvements can lower both training times and resource consumption by an exceptional amount while preserving accuracy, wouldn't that also be true for all sizes of models on all devices?

  2. Old Used Programmer

    256KB, you say?

    That suggests that it would run on a Raspberry Pico, or other RP2040 board.

  3. Arthur the cat Silver badge

    as little as 256KB of SRAM

    Luxury!

    When I wer't lad …

    1. IanRS

      Re: as little as 256KB of SRAM

      ... you had to hand carve the ferrite cores?

      1. Arthur the cat Silver badge

        Re: as little as 256KB of SRAM

        Ferrite? We used to dream of ferrite!

  4. heyrick Silver badge

    I wonder what was the bigger impediment

    The small amount of memory or the low clock speed?

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like