Feasibility analysis of hardware acceleration for AML

This microproject investigated the feasibility of various hardware options particularly in-memory processing hardware acceleration

Micro-project in Humane-AI-Net

Short description

Algebraic Machine Learning (AML) offers new opportunities in terms of transparency and control. However, that comes along with many challenges regarding software and hardware implementations. To understand the hardware needs of this new method it is essential to analyze the algorithm and its computational complexity.

With this understanding, this microproject investigated the feasibility of various hardware options, particularly in-memory processing hardware acceleration for AML.

Additional information

Output

  • Simulation model for a PIM architecture using AML
  • Report

This Humane-AI-Net micro-project was carried out by Algebraic AI S.L. (Fernando Martin Maroto), Technische Universität Kaiserslautern (TUK, Christian Weis) and German Research Centre for Artificial Intelligence (DFKI, Matthias Tschöpe).

Technical categories
Machine learning
Technology Readiness Level
TRL 1-2 (Basic research)

Lead institution

Last updated
Thu, 05/05/2022 - 13:33
Contact details
FERNANDO MARTIN MAROTO (fernando.martinmaroto@fchampalimaud.org)

Assets related to Feasibility analysis of hardware acceleration for AML