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.
(Guest article on the Nous Research blog) Anecdotal evidence suggests open weight models produce significantly more tokens for similar tasks than closed weight models. This report systematically investigates these observations. We confirm this trend to be generally true, but observe significant differences depending on problem domain.
Todays candles have been optimized not to flicker. But it turns out when we bundle three of them together, the resulting triplet will start to naturally oscillate. Amazingly, the frequency is rather stable at ~9.9 Hz as it mainly depends on gravity and diameter of the flame. We detect the oscillation with a suspended wire and divide it down to 1 Hz.
Is it possible to implement reasonably accurate inference of MNIST, the handwritten numbers dataset, on a “3 cent” Microcontroller with only 64 bytes of RAM and 1K of instruction memory?
BitNetMCU is a project focused on the training and inference of low-bit quantized neural networks, designed to run efficiently on low-end microcontrollers like the CH32V003. Quantization aware training (QAT) and fine-tuning of model structure allowed surpassing 99% Test accuracy on a 16x16 MNIST dataset in only 2kb of RAM and 16kb of Flash.
Analyzing a battery powered LED tea light with 24h timer functionality. Discovering that it is surprisingly based on a low-cost 8-bit microcontroller integrated into the LED package.
What would it take to build an addressable LED like the WS2812 (aka Neopixel) using only discrete transistors? Time for a small “1960 style logic meets modern application” technology fusion project.
Flashing a LED is certainly among the first set of problems any burgeoning electronics specialist is tackling, may it be by using an ancient NE555 or, more recently, a microcontroller to control the LED. As it turns out, we can turn any trivial problem into a harder one by changing its constraints.
Can we reverse engineer the flickering pattern of a real candle to improve artificial candle LEDs? Measuring and analyzing the temporal light output of a real candle.
Implementation of the optimized light_ws2812 driver with hand crafted assembly inner loop that bit-bangs LEDs even at 4 MHz without timing violations on an AVR.