Authors: | Yayla, Mikail |
Title: | A vision for edge AI |
Other Titles: | robust binarized neural networks on emerging resource-constrained hardware |
Language (ISO): | en |
Abstract: | Edge Artificial Intelligence is progressively pervading all aspects of our life. However, to perform complex tasks, a massive amount of matrix multiplications needs to be computed. At the same time, the available hardware resources for computation are highly limited. The pressing need for efficiency serves as the motivation for this dissertation. In this dissertation, we propose a vision for highly-resource constrained future intelligent systems that are comprised of robust Binarized Neural Networks operating with approximate memory and approximate computing units, while being able to be trained on the edge. |
Subject Headings: | Embedded system Edge AI Machine learning HW/SW codedesign Non-volatile memory Error tolerance Efficient training |
Subject Headings (RSWK): | Künstliche Intelligenz Eingebettetes System Maschinelles Lernen Fehlertoleranz |
URI: | http://hdl.handle.net/2003/42431 http://dx.doi.org/10.17877/DE290R-24267 |
Issue Date: | 2024 |
Appears in Collections: | Entwurfsautomatisierung für Eingebettete Systeme |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Dissertation_Yayla.pdf | DNB | 2.48 MB | Adobe PDF | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org