The document discusses VEDLIoT, a project that aims to develop very efficient deep learning for IoT applications. It focuses on developing a scalable and heterogeneous hardware platform using accelerators like FPGAs and ASICs. The project also aims to optimize deep learning toolchains for IoT use cases in industries like industrial IoT, automotive, and smart homes. An open call was announced to allow early use and evaluation of the VEDLIoT technology.
2. 2
Platform
Hardware: Scalable, heterogeneous, distributed
Accelerators: Efficiency boost by FPGA and ASIC technology
Toolchain: Optimizing Deep Learning for IoT (Embedl)
Use cases
Industrial IoT
Automotive
Smart Home
Open call
At project mid-term
Early use and evaluation of VEDLIoT technology
Very Efficient Deep Learning for IoT – VEDLIoT
Call: H2020-ICT2020-1
Topic: ICT-56-2020 Next Generation Internet of Things
Duration: 1. November 2020 – 31. Oktober 2023
Coordinator: Bielefeld University (Germany)
Overall budget: 7 996 646.25 €
Consortium: 12 partners from 4 EU countries (Germany,
Poland, Portugal and Sweden) and one associated
country (Switzerland).
More info:
https://www.vedliot.eu/
https://twitter.com/VEDLIoT
https://www.linkedin.com/company/vedliot/
3. 3
Bielefeld University (UNIBI) - Coordinator
Christmann (CHR)
University of Osnabrück (UOS)
Siemens (SIEMENS)
University of Neuchâtel (UNINE)
University of Lisbon (FC.ID)
Chalmers (CHALMERS)
University of Gothenburg (UGOT)
RISE (RISE)
EmbeDL (EMBEDL)
Veoneer (VEONEER)
Antmicro (ANT)
VEDLIOT partners
5. 6
VEDLIoT Hardware Platform
Heterogeneous, modular, scalable microserver system
Supporting the full spectrum of IoT from embedded over the edge towards the cloud
Different technology concepts for improving
x86
GPU
ML-ASIC
ARM v8
GPU
SoC
FPGA
SoC
RISC-V
FPGA
VEDLIOT Cognitive
IoT Platform
Performance
Cost-effectiveness
Maintainability
Reliability
Energy-Efficiency
Safety
7. 16
Flexible and adaptable Accelerators for Deep Learning
DL
Model
DL Model
CPU, GPU-
SoC,
ML-SoC
FPGA-SoC
End of Moore’s law & dark silicon
=> Domain Specific Architectures (DSA)
Efficient, flexible, scalable accelerators for
the compute continuum
Algotecture
Optimized DL algorithms
Optimized toolchain
Optimized computer architecture
Heterogeneous DL
Accelerator
Algotecture/
Co-Designed DL
Accelerator
Compiler
Co-Design
8. 18
VEDLIoT‘s Deep Learning Toolchain
Enabling the rapid convergence of the fast pace
innovation on the hardware and software
Frameworks &
Exchange Formats
Optimization Engine Compilers &
Runtime APIs
Heterogeneous
Hardware
Platforms
9. 19
Increase safety, health and well being of residents – acceleration of AI methods for
demand-oriented user-home interaction
Use case: Smart Home / Assisted Living
10. 21
Face recognition
mobilenetSSD trained on WIDERFACE dataset
Object detection
YoloV3, Efficient-Net, yoloV4-tiny
Gesture detection
YoloV4-tiny with 3 Yolo layers (usually: 2 layers)
Speech recognition
Mozilla DeepSpeech
AI Art: Style-Gan trained on works of arts
Collect usage data in situation memory
Smart Mirror – Neural Networks
11. 22
Industrial IoT – drive condition classification
Control applications need DL-based condition classification
On the edge device for low power consumption
Suggestions for control and maintenance
DL methods on all communication layers
DL in a distributed architecture
Dynamically configured systems
Sensored testbench with 2 motors
Acceleration, Magnetic field, Temperature,
IR-Cam (temperature), Current-Sensors, Torque
On / Off detection without
motor current or voltage
Cooling fault detection
Bearing fault detection
12. 23
Industrial IoT – Arc detection for DC distributions
AI based pattern recognition for different local sensor data
current, magnetic field, vibration, temperature, low resolution infrared picture
Safety critical nature
response time should be <10ms
AI based or AI supported decision made by the sensor node itself or by a local part of the sensor
network
14. 25
The fun has just started!
Follow our work!
https://twitter.com/VEDLIoT
https://www.linkedin.com/company/vedliot/
https://vedliot.eu
Be part of it
Open call at project mid-term
Allow early use and evaluation of VEDLIoT
technology
15. 26
Thank you for your
attention.
Contact
Hans Salomonsson
Embedl, Sweden
hans@embedl.ai
16. 27
End-to-end attestation, support for execution and communication
Support for
End-to-end trust (attestation)
Secrets distribution (keys)
Machine learning (federated, streaming, …)
Requirements
Support for edge applications
Decentralised, dynamic, loosely organised
Rely on
Trusted execution environments
BFT and peer-to-peer algorithms
Blockchain concepts
VEDLIoT
app
Attestation
Pool
17. 28
Simulation platform for IoT
Open source framework for software/hardware co-development with CI-driven testing
capabilities, as well as metrics for measuring efficiency of ML workloads
Enables development and continuous testing of VEDLIoT’s security features and its robustness
Renode is available to all project members and future users of VEDLIoT and will include a
simulated model of the RISC-V-based FPGA SoC platform developed as part of the VEDLIoT
project
18. 29
Safety and robustness
Define monitors for timeliness and data quality assessment
Develop safety argumentation for adaptive solutions,
exploiting architectural hybridization
Hybrid System architecture:
• Some system components implemented
with assured reliability (as needed)
• Remaining components subject to
uncertainties and prone to failures
Safety requirements:
• Defined at design time for each operational
mode
Monitoring data:
• Collected in run-time, to allow verifying if
safety requirements are being satisfied
and trigger reconfiguration if not
Timeliness (e.g., deadline
miss detection)
Sensor data quality (e.g.,
outlier, noise detection)
Accuracy of DL systems
(e.g., anomaly detection)