Zur Kurzanzeige

dc.contributor.advisorWeber, Hartmut
dc.contributor.advisorWeder, Andreas
dc.contributor.authorPfeiffer, Pascal
dc.date.accessioned2024-10-25T07:54:19Z
dc.date.available2024-10-25T07:54:19Z
dc.date.issued2024
dc.identifier.urihttps://publikationsserver.thm.de/xmlui/handle/123456789/383
dc.identifier.urihttp://dx.doi.org/10.25716/thm-330
dc.description.abstractEmbedded AI deals with the execution of neural networks on microcontrollers and other small-scale devices. These systems aim to perform AI tasks on limited hardware resources, without relying on cloud-based services. This thesis presents the extension of an embedded AI framework for floating-point and quantized neural networks. The framework is extended with 1D convolutions, batch normalization, batch normalization folding, concatenation and global pooling while also lowering the memory requirements for quantized neural networks. At the beginning of this thesis, the challenges of embedded AI are explained and the RISC-V IP core used is presented. The embedded AI framework Emmi is introduced, the fundamentals for understanding convolutions and batch normalization are presented, and a brief overview of its features and the quantization technique used is given. Before implementing the extensions, Emmi is analyzed and the requirements are summarized. During the test-driven implementation, unit and integration tests ensure the functionality of the framework. After testing and benchmarking it on a non-vector RISC-V system, it is compiled with automatic vectorization and tested in a RISC-V simulator that supports vector instructions. Finally, it is shown that the framework can be used in a predictive maintenance application.de
dc.format.extent67 S.de
dc.language.isoende
dc.publisherTechnische Hochschule Mittelhessen; Gießende
dc.rights.urihttps://rightsstatements.org/page/InC/1.0/de
dc.subjectNeural Networks, Quantization, DYINQ, RISC-Vde
dc.subject.ddc000 Informatik, Informationswissenschaft und allgemeine Werkede
dc.titleExtension of an Embedded AI Framework for RISC-V Systemsde
dc.title.alternativeErweiterung eines Embedded AI Frameworks für RISC-V Systemede
dc.typeAbschlussarbeit (Master)de
dcterms.accessRightsopen accessde


Dateien zu dieser Ressource

Thumbnail

Das Dokument erscheint in:

Zur Kurzanzeige

Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden:
Urheberrechtlich geschützt