Very Efficient Deep Learning in IOT (VEDLIoT)

Forskningsprojekt, 2020 – 2023

Deltagare

Samarbetspartners

Finansiering

Publikationer

An Efficient Hybrid Deep Learning Accelerator for Compact and Heterogeneous CNNs

An empirical investigation of challenges of specifying training data and runtime monitors for critical software with machine learning and their relation to architectural decisions

Efficient Processing of Compact and Heterogeneous Deep Neural Networks

Extending Vector Processing Units for Enhanced Linear Algebra Performance

Methods for Requirements Engineering, Verification, Security, Safety, and Robustness in AIoT Systems

Identifying and managing data quality requirements: a design science study in the field of automated driving

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs

VEDLIoT: Next generation accelerated AIoT systems and applications

An Investigation of Challenges Encountered When Specifying Training Data and Runtime Monitors for Safety Critical ML Applications

A compositional approach to creating architecture frameworks with an application to distributed AI systems

Evaluation of heterogeneous AIoT Accelerators within VEDLIoT

A Scalable, Heterogeneous Hardware Platform for Accelerated AIoT based on Microservers

RAINBOW: Multi-Dimensional Hardware-Software Co-Design for DL Accelerator On-Chip Memory

ARADA: Adaptive Resource Allocation for Improving Energy Efficiency in Deep Learning Accelerators

Automotive Perception Software Development: An Empirical Investigation into Data, Annotation, and Ecosystem Challenges

Exploiting the Potential of Flexible Processing Units

VEDLIoT: Very Efficient Deep Learning in IoT

FiBHA: Fixed Budget Hybrid CNN Accelerator

VSA: A Hybrid Vector-Systolic Architecture

Mer information

Projektets webbplats

https://vedliot.eu/

Senast uppdaterat