Neural Networks (MNIST inference) on the “3-cent” Microcontroller

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?

Implementing Neural Networks on the “10-cent” RISC-V MCU without Multiplier

I have been meaning for a while to establish a setup to implement neural network based algorithms on smaller microcontrollers. After reviewing existing solutions, I felt there is no solution that I really felt comfortable with. One obvious issue is that often flexibility is traded for overhead. As always, for a really optimized solution you have to roll your own. So I did. You can find the project here and a detailed writeup here.

It is always easier to work with a clear challenge: I picked the CH32V003 as my target platform. This is the smallest RISC-V microcontroller on the market right now, addressing a $0.10 price point. It sports 2kb of SRAM and 16kb of flash. It is somewhat unique in implementing the RV32EC instruction set architecture, which does not even support multiplications. In other words, for many purposes this controller is less capable than an Arduino UNO.