Faster and More Energy Efficient Machine Learning for Embedded Systems
EmbeDL is a Software Development Kit installed on premises to optimise complex DL models on embedded hardware systems. It empowers product manufacturers by providing them with the entire toolchain and services necessary to acceler...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
PDC2021-121847-I00
SISTEMAS ADAPTATIVOS EN HARDWARE DE REDES NEURONALES PROFUND...
91K€
Cerrado
SEA2Learn
SElf-Adaptive and Automated LEARNing Framework for Smart Sen...
176K€
Cerrado
ALOHA
software framework for runtime Adaptive and secure deep Lear...
6M€
Cerrado
NEUROKIT2E
Open source deep learning platform dedicated to Embedded har...
19M€
Cerrado
SENSATION
Self Energy Supporting Autonomous Computation
3M€
Cerrado
Hailo-8
End to end hardware implementation of Artificial Neural Netw...
3M€
Cerrado
Información proyecto EmbeDL
Duración del proyecto: 24 meses
Fecha Inicio: 2023-03-19
Fecha Fin: 2025-03-31
Líder del proyecto
EMBEDL AB
No se ha especificado una descripción o un objeto social para esta compañía.
TRL
4-5
Presupuesto del proyecto
4M€
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
EmbeDL is a Software Development Kit installed on premises to optimise complex DL models on embedded hardware systems. It empowers product manufacturers by providing them with the entire toolchain and services necessary to accelerate their AI-driven system development and launch into production. What is currently taking months, years or abandoned R&D, can now be done in weeks. Using the EmbeDL platform, the product development team can:
-Automatically optimise a DL model for specific hardware while meeting energy consumption, hardware cost, and other requirements, by pruning/compressing a state of the art model in a hardware and requirements-aware fashion or searching automatically for the optimal model.
-Automatically evaluate hardware for its model (currently existing as an internal tool to be developed into a full fledged product), by a combination of predictive methods and hardware-in-the-loop.
-Accelerate the development cycle with easy to use and highly automated tools.