BB-KI Chips

Brandenburg and Bayern Action for AI Hardware

About

Artificial Intelligence (AI) plays a crucial role in digitization and future prosperity. However, AI-specific hardware is still underrepresented in university teaching, despite its growing importance in platforms from companies like Xilinx, NVIDIA, ARM, and Intel.

In Germany, AI-capable hardware is especially important due to privacy concerns with cloud-based data processing. Technologies like Industry 4.0, 6G, smart cities, autonomous driving, and IoT require edge computing to ensure sensitive data is processed locally.

Currently, university education barely covers AI hardware due to disciplinary separation. This project aims to create a hybrid, cross-university program combining theory, design, and application, with hands-on experience in chip production in Germany.

The project is supported by Leibniz Institute IHP (Frankfurt/O.), allowing students to work on real AI hardware.

Consortium members:

  • University of Potsdam:
    • Prof. Milos Krstic, Institute of Computer Science (overall project lead)
    • Prof. Benno Stabernack, Institute of Computer Science
    • Prof. Ulrike Lucke, Institute of Computer Science
    • Prof. Oliver Korup, Institute of Environmental Science and Geography
  • Technical University of Munich:
    • Prof. Martin Schulz / Prof. Carsten Trinitis, School of Computation, Information and Technology
    • Prof. Martin Werner, School of Engineering and Design
    • Prof. Daniel Cremers, School of Computation, Information and Technology

Funding: 4 million euros from BMFTR (2021–2025), with 340,000 euros for this sub-project.

Funder

BMFTR Logo

Partnership

University of Potsdam Logo Technical University of Munich Logo

Teaching Activities

University of Potsdam:

  • Chair of Professor Milos Krstic – Design and Test Methodology:
    • Chip Design (6 ECTS)
    • Processor Design for AI Applications: From System to Transistor (6 ECTS, BSc & MSc)
    • Hardware Architectures for AI Applications (6 ECTS, BSc & MSc)
    • Hardware Defects, Faults, Errors, and Failures: Yield, Reliability, and Dependability (6 ECTS, BSc & MSc)
    • Seminar on Neuromorphic Chip Design (3 ECTS, BSc & MSc)
  • Chair of Professor Benno Stabernack – Embedded Systems Architectures for Signal Processing:
    • System on Chip Architectures (6 ECTS, BSc & MSc)
    • Computer Vision Hardware Architecture (3 ECTS, BSc & MSc)
  • Chair of Professor Ulrike Lucke – Complex Multimedia Application Architectures:
    • Seminar: Ethics for Nerds (3 ECTS, BSc & MSc)

Technical University of Munich:

  • Chair of Professor Martin Schulz / Professor Carsten Trinitis – Computer Architecture and Parallel Systems:
    • Practical Course: Accelerating Convolutional Neural Networks using Programmable Logic (10 ECTS, BSc & MSc) (Prof. Schulz)
    • Seminar Course: Development and Integration of Hardware Accelerators (5 ECTS, BSc & MSc) (Prof. Schulz)
    • Seminar: Ethics for Nerds (6 ECTS, BSc & MSc) (Prof. Trinitis)
    • Practical Course: Introduction to Hardware Design Languages and Tools (6 ECTS, BSc) (Prof. Trinitis)
  • Chair of Professor Martin Werner – Big Geospatial Data Management:
    • Selected Topics in Big Geospatial Data (5 ECTS, BSc & MSc)
    • Lab Course Mobile Computer Vision (5 ECTS, BSc)
    • Lab Course Photogrammetric Data Acquisition (5 ECTS, BSc)
    • Engineering Projects (6 ECTS, BSc)

Joint Curriculum “Edge AI”

Course Title ECTS Course Hours Performance Evaluation
Chip Design 6 4 hours/week Project & oral exam
Processor Design for AI Applications: From System to Transistor 6 4 hours/week Oral exam
Hardware Architectures for AI Applications 6 4 hours/week Oral exam
Seminar on Neuromorphic Chip Design 3 2 hours/week Presentation & report
System on Chip Architectures 6 4 hours/week Project & presentation
Computer Vision Hardware Architecture 3 2 hours/week Presentation & report
Practical Course: Accelerating Convolutional Neural Networks using Programmable Logic 10 Project, presentation & report
Seminar Course: Development and Integration of Hardware Accelerators 5 Presentation & report

Highlights

Sobel Demonstrator
Virtual Lab Image 1
Virtual Lab Image 2
Student Lab Image 1
Student Lab Image 2
Student Lab Image 3
CI Artefact
Werner Setup
Inside View
Bird Detection
Jena Workshop 1
Jena Workshop 2
Students 1
Students 2
Summer School 1
Summer School 2
Summer School 3

Publications

  1. Raja, S. P., et al. "Crop prediction based on characteristics of the agricultural environment using various feature selection techniques and classifiers." IEEe Access 10 (2022): 23625-23641.
  2. Xiong, Zhouyi, et al. "Integrating AI Hardware in Academic Teaching: Experiences and Scope from Brandenburg and Bavaria." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 10 (2023): 75-81.
  3. Gundla, Sri Charan, et al. "A feature extraction approach for the detection of phishing websites using machine learning." Journal of Circuits, Systems and Computers 33.02 (2024): 2450031.
  4. Sudhir, A., et al. "A Machine Learning Approach to Spam Detection in Social Media Feeds." 2023 IEEE 33rd International Conference on Microelectronics (MIEL). IEEE, 2023.
  5. Gundla, Sri Charan, et al. "A feature extraction approach for the detection of phishing websites using machine learning." Journal of Circuits, Systems and Computers 33.02 (2024): 2450031.
  6. Poudel, Utsav, et al. "Applicability of ocr engines for text recognition in vehicle number plates, receipts and handwriting." Journal of Circuits, Systems and Computers 32.18 (2023): 2350321.
  7. Arango Carmona, M. I., et al. "A multi-hazard perspective on the São Sebastião-SP event in February 2023: What made it a disaster." XXV Brazilian Symposium on Water Resources (Aracaju, Brazil, 19–24 November 2023), https://anais. abrhidro. org. br/job. php. 2023.
  8. Vijay Nikhil, U., Z. Stamenkovic, and S. P. Raja. "A Study of Elliptic Curve Cryptography and Its Applications." International Journal of Image and Graphics (2024): 2550062.
  9. Mariammal, G., et al. "A Novel Ensemble Machine Learning Algorithm for Predicting the Suitable Crop to Cultivate Based on Soil and Environment Characteristics Un nouvel algorithme d’apprentissage automatique d’ensemble pour Prédire la culture appropriée à cultiver en fonction des Caractéristiques du sol et de l’environnement." IEEE Canadian Journal of Electrical and Computer Engineering (2024).
  10. Nikhil, Uppugunduri Vijay, et al. "Machine learning-based crop yield prediction in south india: performance analysis of various models." Computers 13.6 (2024): 137.
  11. Zhao, Dedong, et al. "ImSTDP: Implicit Timing On-Chip STDP Learning." IEEE Transactions on Circuits and Systems I: Regular Papers (2024).
  12. Kreowsky, Philipp, Justin Knapheide, and Benno Stabernack. "An Approach Towards Distributed DNN Training on FPGA Clusters." International Conference on Architecture of Computing Systems. Cham: Springer Nature Switzerland, 2024.
  13. Luna, Lisa Victoria, et al. "Urban landslides triggered under similar rainfall intensities in cities globally." Authorea Preprints (2024).
  14. Sidhaarth, Tarran, et al. "Enhanced Miss Forest and Multivariate Time Series Prediction of Wind Speed Using Deep Learning." Journal of Circuits, Systems and Computers (2025): 2530006.
  15. Vijay Nikhil, U., Z. Stamenkovic, and S. P. Raja. "A Study of Elliptic Curve Cryptography and Its Applications." International Journal of Image and Graphics (2024): 2550062.
  16. Arango-Carmona, Maria Isabel, et al. "Hillslope-Torrential Hazard Cascades in Tropical Mountains." EGUsphere 2025 (2025): 1-30.

Events

No events are scheduled at this time.

Jobs

No positions are available at this time.