Welcome to EnviroDIY, a community for do-it-yourself environmental science and monitoring. EnviroDIY is part of WikiWatershed, an initiative of Stroud Water Research Center designed to help people advance knowledge and stewardship of fresh water.
New to EnviroDIY? Start here

Reply To: Mayfly sketch compiles, seems to upload, but doesn’t

Home Forums Mayfly Data Logger Mayfly sketch compiles, seems to upload, but doesn’t Reply To: Mayfly sketch compiles, seems to upload, but doesn’t

#18022
neilh20
Participant

    So good to play around with it, I asked bard.google.com a question that doesn’t have a lot written about it ..

    “What is the quiescent power consumption of the Bristlemouth hardware”

    AND it sounds coherent – however its “hallucinating”  as not a google project. The 10milliwatts its quoting is the active transmission per Mhz.

    I’ve got an open question to the designers .. (https://www.bristlemouth.org/  https://bristlemouth.discourse.group/t/what-is-the-expected-power-profile-and-quiescent-current/65)

     

    Bard Answer:
    <p data-sourcepos=”1:1-1:316″>The quiescent power consumption of the Bristlemouth hardware is 10 milliwatts (mW). This means that the hardware consumes very little power when it is not actively processing data. This makes it ideal for applications where power consumption is a critical factor, such as battery-powered devices or embedded systems.</p>
    <p data-sourcepos=”3:1-3:270″>The Bristlemouth hardware is a neural network accelerator developed by Google AI. It is designed to be highly energy efficient, while still providing high performance. The quiescent power consumption of 10 mW is achieved through a number of design techniques, including:</p>

    <ul data-sourcepos=”5:1-8:0″>
    <li data-sourcepos=”5:1-5:29″>Using a low-power processor
    <li data-sourcepos=”6:1-6:24″>Using low-power memory
    <li data-sourcepos=”7:1-8:0″>Using a power-gating mechanism to turn off components when they are not in use

    <p data-sourcepos=”9:1-9:220″>The Bristlemouth hardware is a significant improvement over previous generations of neural network accelerators in terms of power efficiency. This makes it a valuable tool for developing energy-efficient AI applications.</p>