Groups | Search | Server Info | Login | Register


Groups > comp.arch.embedded > #32251

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

Date 2024-10-26 20:43 -0500
Subject Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller
Newsgroups comp.misc, comp.ai.philosophy, alt.microcontrollers, comp.arch.embedded, alt.microcontrollers.8bit
References <GDBnsQalznyGTjeHEuVJnPScMPMUvCQe@news.usenet.farm>
From olcott <NoOne@NoWhere.com>
Message-ID <mImdnbief8Y4B4D6nZ2dnZfqlJydnZ2d@giganews.com> (permalink)

Cross-posted to 5 groups.

Show all headers | View raw


On 10/21/2024 3:06 PM, D. Ray wrote:
> 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>

test to see if this posts or I should dump this paid provider.

-- 
Copyright 2024 Olcott

"Talent hits a target no one else can hit;
  Genius hits a target no one else can see."
  Arthur Schopenhauer

Back to comp.arch.embedded | Previous | NextPrevious in thread | Next in thread | Find similar


Thread

Neural Networks (MNIST inference) on the “3-cent” Microcontroller D. Ray <d@ray> - 2024-10-21 20:06 +0000
  Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller Don Y <blockedofcourse@foo.invalid> - 2024-10-21 15:09 -0700
  Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller George Neuner <gneuner2@comcast.net> - 2024-10-22 15:39 -0400
    Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller D. Ray <d@ray> - 2024-10-28 15:42 +0000
      Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller David Brown <david.brown@hesbynett.no> - 2024-10-28 17:50 +0100
  Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller olcott <NoOne@NoWhere.com> - 2024-10-26 20:43 -0500
    Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller George Neuner <gneuner2@comcast.net> - 2024-10-27 16:41 -0400
    Re: Neural Networks (MNIST inference) on the “3-cent” Microcontroller D. Ray <d@ray> - 2024-10-28 15:42 +0000

csiph-web