News, tips, advice, support for Windows, Office, PCs & more. Tech help. No bull. We're community supported by donations from our Plus Members, and proud of it
Home icon Home icon Home icon Email icon RSS icon
  • Apple News Wrap Up: November 28, 2020

    Posted on Nathan Parker Comment on the AskWoody Lounge

    Home Forums AskWoody support Non-Windows operating systems macOS Apple News Wrap Up: November 28, 2020

    Viewing 4 reply threads
    • Author
      Posts
      • #2315594
        Nathan Parker
        AskWoody_MVP

        Nathan Parker

        2 users thanked author for this post.
      • #2315619
        OscarCP
        AskWoody Plus

        According to the first article linked by Nathan: “The M1 chip has a built-in Neural Engine, a component that Apple first started adding to its A-series chips a few years ago. The Neural Engine is designed to accelerate machine learning tasks across the Mac for things like video analysis, voice recognition, image processing, and more.

        I wish someone would give a concrete example of who, when and how may take advantage of this kind of specialized electronics included in the M1 chips. If one is working on voice recognition, for example, then would be using software that is designed for doing that. Is anyone designing, or likely to design such software to make use of the Neural Engine?

        Windows 7 Professional, SP1, x64 Group W (ex B) & macOS Mojave + Linux (Mint)

        2 users thanked author for this post.
        • #2315635
          Alex5723
          AskWoody Plus

          The Neural Engine — what do we know about it?

          Most new iPhones and iPads have a Neural Engine, a special processor that makes machine learning models really fast, but not much is publicly known about how they actually work.

          The Apple Neural Engine (or ANE) is a type of NPU, which stands for Neural Processing Unit. It’s like a GPU, but instead of accelerating graphics an NPU accelerates neural network operations such as convolutions and matrix multiplies.

          The ANE isn’t the only NPU out there — many companies besides Apple are developing their own AI accelerator chips. Besides the Neural Engine, the most famous NPU is Google’s TPU (or Tensor Processing Unit)…..

          3 users thanked author for this post.
      • #2315803
        Nathan Parker
        AskWoody_MVP

        Really looking forward to seeing apps take advantage of the Neural Engine. The results will be amazing.

        Nathan Parker

      • #2316049
        OscarCP
        AskWoody Plus

        Nathan: “Really looking forward to seeing apps take advantage of the Neural Engine. The results will be amazing.

        Doing a bit of research into this, I’ve found that the iPhones and iPads have already had, for a while, ARM architecture RISC CPUs with Neural Engines used to facilitate certain tasks, and that now Apple has come up with a new chip, the M1, that is a modified version of the latest iPhone one, the A12 also known as “Bionic”:

        https://arstechnica.com/gadgets/2020/08/apple-explains-how-it-uses-machine-learning-across-ios-and-soon-macos

        I do not now what MS will do, although I understand that there has been a research project there on ARM-architecture PCs and on the corresponding Windows ARM-compatible version. But this is research and not necessarily a promise of new kinds of PCs and a new “ARM” Windows.

        Now, I have been puzzled for a while, because the design of the ARM architecture of the CPU cores belongs to a company called “ARM Holdings” and this company licenses others the right to build CPU chips with cores that have this exact architecture. But it turns out that there are different types of licenses and with one of them, called, unsurprisingly enough, the “architecture license”, the cores can be designed differently by the license holder, but following some strict rules stated in the license. So I imagine that Apple has got one of those licenses in order to design their so-called “ARM-based” chips.

        Finally, besides the use of machine learning in business and consumer-type applications, such as, in tablets, recognizing the writer of the text or signature being written on it, as well as to improve certain tasks native to Macs (meaning the ones by Apple already installed when one buys one), I find the introduction of the Neural Engine into the Mac’s chipset as the start of a promising development for the use of PCs in engineering and scientific tasks. For example, one kind I am familiar with is the analysis of very large amounts of spacecraft-collected data in order to extract, out of the incoming firehose-like outpour of information, the trickle of certain small but important features one needs to see. It is difficult enough to develop software for doing this using conventional data analysis techniques, but in certain important cases the use of machine learning to train a neural circuit to recognize those features could be of great help, perhaps making a big difference for the better.

        Windows 7 Professional, SP1, x64 Group W (ex B) & macOS Mojave + Linux (Mint)

        1 user thanked author for this post.
      • #2316063
        Nathan Parker
        AskWoody_MVP

        Yep, iOS devices have had the Neural engine for a little bit, which is why I’m excited to see it on the Mac. We’ve already had a taste of what it can do in small/mobile devices. Having it on more powerful Macs will be super exciting.

        All I can say is, if you think you’ve enjoyed your Intel Mac, you’ll love eventually using an Apple Silicon Mac.

        Nathan Parker

        2 users thanked author for this post.
    Viewing 4 reply threads

    Please follow the -Lounge Rules- no personal attacks, no swearing, and politics/religion are relegated to the Rants forum.

    Reply To: Apple News Wrap Up: November 28, 2020

    You can use BBCodes to format your content.
    Your account can't use Advanced BBCodes, they will be stripped before saving.

?
This website collects data via Google Analytics. Click here to opt in. Click here to opt out.
×