Fraunhofer Institute for Integrated Circuits IIS
Fraunhofer Institute for Integrated Circuits IIS
3D render AI artificial intelligence technology CPU central processor unit chipset on the printed circuit board for electronic and technology concept select focus shallow depth of field
© istock

© iStock

Efficient AI

Energy efficient AI for the future - on-device inference and training

Fast, private, energy-efficient, close to sensors, self-learning, mobile

Whether for automating processes or analyzing large volumes of data: Intelligent and self-learning systems are becoming increasingly important in business processes. Until now, these intelligent systems have always had to be connected to a cloud, as this provides the necessary computing power for AI models. With Edge AI, short for Edge Artificial Intelligence, the next generation of intelligent systems is now entering the home: intelligence is being transferred directly to the end devices.

Privacy warning

With the click on the play button an external video from www.youtube.com is loaded and started. Your data is possible transferred and stored to third party. Do not start the video if you disagree. Find more about the youtube privacy statement under the following link: https://policies.google.com/privacy

Benefits of Edge AI

Energy Efficiency and Resource Conservation

The TinyML needs up to a thousand times less power to run ML applications compared to a standard GPU. The reason for this is, among other things, the local execution of the models instead of sending the data back and forth. For this reason, the TinyML devices can run for years without batteries, depending on the use case.

The size of the batteries required and thus the use of valuable resources is also reduced due to the considerable energy savings.

Realtime

 

Since the model is run locally, in order to perform inference, the raw data does not need to be sent to the cloud first and then sent back when processed. This reduces output latency as well as communication bandwidth requirements, which in turn enables rapid response.

Independence, Privacy and Security

The user is not dependent on a cloud service provider. Since the data does not have to be shared with external parties, this point ultimately also contributes to the protection of privacy.

In addition, there is no dependence on a communication link. The risk of possible interference during transmission between the embedded system and the cloud is therefore eliminated.

Become a Certified Data Scientist Specialized in TinyML

TinyML enables machine learning on microcontrollers and opens doors to a wide range of application areas. The course is designed for specialists with data analysis experience and hardware developers who want to improve their knowledge of machine learning.

You will learn how to develop ML applications on microcontrollers, recognize challenges at an early stage and develop appropriate strategies. Use our comprehensive know-how for your success.

Our Service Offer

Research and Development

We offer you partial or complete R&D services.

 

  • Embedded AI: development tool for developing embedded AI solutions to reduce costs and improve the quality of your application.
  • Optimized AI model for your hardware: a tailor-made solution adapted to your hardware with optimized performance through AI.
  • Mentoring : We accompany you in your R&D projects from data acquisition to the development of an AI model.

Consulting

We advise and support you with your individual concerns relating to your AI solutions.

 

 

  • Potential analyses: We carry out a quick potential analysis of your personal concerns.
  • Directional decisions: We provide you with groundbreaking support by creating an automated report to help you make initial directional decisions on your personal project.
  • Hardware recommendations: We advise you on suitable hardware and give you recommendations for use in your AI solution.
  • Personal support: Our interdisciplinary team and the network at IIS will support you with your personal project.

Licensing

We may have already developed the right AI model and this can be integrated directly into your use case or licensed by you.

 

We optimize your application through standardized processes and extensive automation of time-intensive work specifically adapted to your use case.

Through training and automatic reduction of complex AI models by removing redundancies, we generate optimal AI models in terms of accuracy and efficiency.

We support you with rapid integration!

© pressmaster - Fotolia.com

Certified Training

We provide you with a quick introduction to AI solutions. Our range of training courses includes AutoML webinars, skills training and seminars on various AI topics.

 

We would be happy to use your data for a customized seminar!

Contact us!

We realize the efficient processing of your R&D projects, as well as the training of junior staff with this new competence profile.

Contact us
for an individual consultation at

machine-learning-lv@iis.fraunhofer.de

Use Cases

 

© Adobe Stock

Vision

From agriculture and biodiversity to people counting.

AI analysis directly behind the camera sensor enables numerous new applications without sending a lot of raw data to the cloud. Privacy remains protected at all times.

Vision
 

Condition Monitoring

Using machine learning in embedded systems to monitor the status of systems and machines in order to be able to react at an early stage or increase efficiency.

Condition Monitoring

© Adobe Stock

Retail

We've all been there: long queues at the checkout again.

With privacy-protecting AI on edge devices, seamless shopping is already possible.

This leaves more time for the finer things.

 

© Fraunhofer IIS/Kurt Fuchs

Sports

Machine learning in embedded systems, e.g. wearables for sports applications such as fitness, soccer, boxing or basketball.

Sports
 

© Adobe Stock / RocknRoller Studios - stock.adobe.com

Speech & Audio

Machine learning in embedded sensor modules for cognitive speech and audio analysis. The audio commands are recognized without a cloud connection.

Audio Demo
 

© Fraunhofer IIS

Tools

Machine learning in embedded sensor modules for cognitive hand tools to recognize assembly processes and ensure quality.

KI4Tools

Overview of concrete services

We offer complete packages that can be used as a whole or in components according to your requirements. All components can be combined in any way and adapted to your needs.

Expand all Close all

Joint Lab

We have very good experience with our customers in so-called "Fast Track Joint Labs": Together with you we develop a first solution for your embedded AI application within one month.

Typically the process is as follows:

  • Kick-Off
  • Selection of the required components of the solution
  • Fast Proof-of-Concept 
  • Interim review of the results
  • Joint development of the final AI application

As a result, an executable solution is created and the know-how is exchanged during the project.

What do you get?

  • We guide you quickly through a joint project to the finished AI pipeline in C/C++ or Python.
  • Jointly developed software components enable you to replicate the development process

If you already have a data set, a proof-of-concept can emerge after just a few days.

Your benefits

  • Know-how transfer happens during the project, not afterwards
  • Your employees become AI experts for processing your applications (integrated training)

Edge AI Suite

Some of our customers increasingly rely on AI functions in their products. To enable them to act independently, we provide a software suite with which our customers can develop, evaluate and deploy embedded AI pipelines themselves.

What do you get?

  • Edge AI suite in the form of coordinated Jupyter notebooks and libraries developed by Fraunhofer in the background
  • Export of final AI pipelines for embedded systems.
  • Adaptation of the software suite to your problems, e.g. processing of specific data sources (sensor data, audio, video)
  • A half-day introductory workshop, if possible on the basis of your own data

Optional

  • We recommend the combination with the seminar to build up extended know-how.
  • Support for one year, if necessary also incl. development hours
  • We are also happy to support you during the final integration, e.g. in the form of a joint lab (see on the right side).

Your benefits

  • Enormous know-how transfer through best practices implemented in the Edge AI suite
  • Immediate ability to act in your AI projects
  • We do not leave you alone in your projects.

Training

We offer a two-day Zero-to-Hero seminar in order to be able to implement the basics of machine learning in a practical way. The seminar can be tailored to you with the help of your data, if you want further training for your organizational unit.

What do you get?

  • With your data and wishes, we create an adapted version of our proven ML Seminar.
  • Your participating employees will learn the basics of machine learning including best practices in theory and with practical examples.
  • You will receive the seminar materials including the source code used (Jupyter notebooks).

Your benefits

  • Quickly build up knowledge in your own team
  • Knowledge that can be put into practice immediately

In a potential analysis (report in *PDF form) of your data set or your problem, you will receive answers to the following questions:

  • How well is your problem solvable?
  • Which AI processing chains meet your requirements?

What do you get?

  • Overview of power requirements / computational demand vs. achievable performance of AI pipelines on embedded hardware
  • The report contains an overview of Pareto-optimal solutions with both classical ML and Deep Learning.
  • → How to decide:
    • Is there a compelling need for Deep Learning?
    • On which hardware does a solution fit best?

Your benefits

  • Quick assessment of the feasibility on your hardware
  • Early information on hardware decisions