Skip to content

Tim's Blog

Tag: ai

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

  • Light_WS2812 library V2.0 - Part I: Understanding the WS2812
  • The "terrible" 3 cent MCU - a short survey of sub $0.10 microcontrollers.
  • Hacking a Candleflicker LED
  • Building a Chaotic Oscillator from Common Components
  • Neural Networks (MNIST inference) on the "3-cent" Microcontroller

Categories

  • Analog Design (1)
  • ARM (1)
  • AVR (7)
  • candle (3)
  • Discrete Logic (3)
  • Hack (11)
  • Hardware (23)
  • Intelligent LED (8)
  • LED (25)
  • machine learning (2)
  • Micronucleus (2)
  • Multiplexing (2)
  • Padauk (5)
  • PFS154 (5)
  • PMS150C (2)
  • Reverse engineering (12)
  • RISC-V (3)
  • Uncategorized (18)
  • USB (3)

Pages

  • About
Tim's Blog 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 97 other subscribers
    • Already have a WordPress.com account? Log in now.
    • Tim's Blog
    • Subscribe Subscribed
    • Sign up
    • Log in
    • Report this content
    • View site in Reader
    • Manage subscriptions
    • Collapse this bar
 

Loading Comments...