There are 0 repository under mlcommons topic.
MLCube® is a project that reduces friction for machine learning by ensuring that models are easily portable and reproducible.
This repository contains the spreadsheet of the quantitative analysis performed for the paper "Suitability of Forward-Forward and PEPITA Learning to MLCommons-Tiny benchmarks".
As described in "Towards Full On-Tiny-Device Learning: Guided Search for a Randomly Initialized Neural Network"
mlcommons tiny performance benchmark on EBAZ4205 (former bitcoin mining board built around Xilinx Zynq-7000 SoC)