| Sysop: | Amessyroom |
|---|---|
| Location: | Fayetteville, NC |
| Users: | 35 |
| Nodes: | 6 (1 / 5) |
| Uptime: | 20:41:36 |
| Calls: | 333 |
| Calls today: | 1 |
| Files: | 989 |
| D/L today: |
1 files (14K bytes) |
| Messages: | 111,473 |
| Posted today: | 1 |
test to see if this posts or I should dump this paid provider.
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>