Skip to content

Tim's Blog

Tag: CH32V002

BitNetMCU with CNN: >99.5% MNIST accuracy on a low-end Microcontroller

Combining a deep-depthwise CNN architecture with variable quantization in BitNetMCU achieves state-of-the-art MNIST accuracy on a low-end 32-bit microcontroller with 4 kB RAM and 16 kB flash.

Read the article at my new blog location.

Unknown's avatarAuthor cpldcpuPosted on November 9, 2025Categories machine learning, RISC-VTags ai, CH32V002, CNN, Convolutional Neural Network, MLLeave a comment on BitNetMCU with CNN: >99.5% MNIST accuracy on a low-end Microcontroller

Top Posts & Pages

  • Controlling RGB LEDs With Only the Powerlines: Anatomy of a Christmas Light String
  • Candle Flame Oscillations as a Clock
  • A surprising IC in a LED light chain.
  • Hacking a Candleflicker LED
  • Revisiting Candle Flicker-LEDs: Now with integrated Timer

Categories

  • Analog Design (1)
  • ARM (1)
  • AVR (7)
  • candle (3)
  • Discrete Logic (3)
  • Hack (12)
  • Hardware (26)
  • Intelligent LED (9)
  • LED (27)
  • machine learning (3)
  • Micronucleus (2)
  • Multiplexing (3)
  • Padauk (5)
  • PFS154 (5)
  • PMS150C (2)
  • Reverse engineering (12)
  • RISC-V (4)
  • Uncategorized (18)
  • USB (3)

Pages

  • About
Tim's Blog Create a free website or blog at WordPress.com.
Privacy & Cookies: This site uses cookies. By continuing to use this website, you agree to their use.
To find out more, including how to control cookies, see here: Cookie Policy
  • Subscribe Subscribed
    Tim's Blog
    Join 102 other subscribers

    Have a WordPress.com account? Log in now.

  • Tim's Blog
    View site in Reader
    Manage subscriptionsSign upLog in
    Report this content
    Collapse this bar
Loading Comments...