1. Forum
  2. Usenet
  3. COMP.AI.PHILOSOPHY

  • =?UTF-8?Q?Neural=20Networks=20(MNIST=20inference)=20on?= =?UTF-8?Q?=20t

    From D. Ray@21:1/5 to All on Mon Oct 21 20:06:28 2024
    XPost: comp.misc, alt.microcontrollers, comp.arch.embedded
    XPost: alt.microcontrollers.8bit

    Bouyed by the surprisingly good performance of neural networks with quantization aware training on the CH32V003, I wondered how far this can be pushed. How much can we compress a neural network while still achieving
    good test accuracy on the MNIST dataset? When it comes to absolutely
    low-end microcontrollers, there is hardly a more compelling target than the Padauk 8-bit microcontrollers. These are microcontrollers optimized for the simplest and lowest cost applications there are. The smallest device of the portfolio, the PMS150C, sports 1024 13-bit word one-time-programmable
    memory and 64 bytes of ram, more than an order of magnitude smaller than
    the CH32V003. In addition, it has a proprieteray accumulator based 8-bit architecture, as opposed to a much more powerful RISC-V instruction set.

    Is it possible to implement an MNIST inference engine, which can classify handwritten numbers, also on a PMS150C?

    …

    …

    <https://cpldcpu.wordpress.com/2024/05/02/machine-learning-mnist-inference-on-the-3-cent-microcontroller/>

    <https://archive.md/DzqzL>

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From olcott@21:1/5 to D. Ray on Sat Oct 26 20:43:01 2024
    XPost: comp.misc, alt.microcontrollers, comp.arch.embedded
    XPost: alt.microcontrollers.8bit

    On 10/21/2024 3:06 PM, D. Ray wrote:
    Bouyed by the surprisingly good performance of neural networks with quantization aware training on the CH32V003, I wondered how far this can be pushed. How much can we compress a neural network while still achieving
    good test accuracy on the MNIST dataset? When it comes to absolutely
    low-end microcontrollers, there is hardly a more compelling target than the Padauk 8-bit microcontrollers. These are microcontrollers optimized for the simplest and lowest cost applications there are. The smallest device of the portfolio, the PMS150C, sports 1024 13-bit word one-time-programmable
    memory and 64 bytes of ram, more than an order of magnitude smaller than
    the CH32V003. In addition, it has a proprieteray accumulator based 8-bit architecture, as opposed to a much more powerful RISC-V instruction set.

    Is it possible to implement an MNIST inference engine, which can classify handwritten numbers, also on a PMS150C?

    …

    …

    <https://cpldcpu.wordpress.com/2024/05/02/machine-learning-mnist-inference-on-the-3-cent-microcontroller/>

    <https://archive.md/DzqzL>

    test to see if this posts or I should dump this paid provider.

    --
    Copyright 2024 Olcott

    "Talent hits a target no one else can hit;
    Genius hits a target no one else can see."
    Arthur Schopenhauer

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)
  • From D. Ray@21:1/5 to olcott on Mon Oct 28 15:42:41 2024
    XPost: alt.microcontrollers, comp.misc, comp.arch.embedded
    XPost: alt.microcontrollers.8bit

    olcott <NoOne@NoWhere.com> wrote:
    On 10/21/2024 3:06 PM, D. Ray wrote:
    Bouyed by the surprisingly good performance of neural networks with
    quantization aware training on the CH32V003, I wondered how far this can be >> pushed. How much can we compress a neural network while still achieving
    good test accuracy on the MNIST dataset? When it comes to absolutely
    low-end microcontrollers, there is hardly a more compelling target than the >> Padauk 8-bit microcontrollers. These are microcontrollers optimized for the >> simplest and lowest cost applications there are. The smallest device of the >> portfolio, the PMS150C, sports 1024 13-bit word one-time-programmable
    memory and 64 bytes of ram, more than an order of magnitude smaller than
    the CH32V003. In addition, it has a proprieteray accumulator based 8-bit
    architecture, as opposed to a much more powerful RISC-V instruction set.

    Is it possible to implement an MNIST inference engine, which can classify
    handwritten numbers, also on a PMS150C?

    …

    …

    <https://cpldcpu.wordpress.com/2024/05/02/machine-learning-mnist-inference-on-the-3-cent-microcontroller/>

    <https://archive.md/DzqzL>

    test to see if this posts or I should dump this paid provider.

    It worked.

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)