BioAI: Bio-Computing for Sustainable and Trustworthy Artificial Intelligence Computation

Mentored by Frank Fitzek, Ivo Sbalzarini, Stefanie Speidel
at TU Dresden

Today, artificial intelligence (AI) computations consume a lot of energy. In addition, the exponential growth in human data production, i.e. the growing amount of data to be transported, stored and computed, has created a need for energy-efficient computing paradigms. Furthermore, research has shown that digital machines cannot compute all tasks. Bio-computing is seen as a way to address these challenges of energy efficiency and computability.

This project aims to investigate the role of bio-computing in AI computation, with a particular focus on medical applications. In collaboration with the National Center for Tumor Disease (NCT), the project will explore how bio-computing could be applied in medical environments, for example to improve diagnostics or biomedical research. Another key milestone will be the integration of bio-computing platforms into existing infrastructure, which will also be considered in the project.

The main research questions in this context would be:

• Which bio-computing platforms, such as the Cortical Labs CL-1, exist for AI computations? What are current challenges and limitations?
• Which medical applications can be mapped to bio-computing platforms?
• Are there any medical computing tasks that digital machines cannot solve but may be suitable for bio-computing platforms?
• What does the interface to at least one bio-computing platform look like? Can we integrate this platform into existing clinical infrastructures?
• What are the key performance indicators for evaluating the performance of the bio-computing platform?
• How does the bio-computing platform scale?

© Cortical Labs, Melbourne, Australia

Cortical Labs CL-1

Work environment

You will work at the Deutsche Telekom Chair of Communication Networks at TU Dresden, in collaboration with the Chair of Scientific Computing for Systems Biology at TU Dresden and the National Center of Tumor Disease (NCT) at UKD Dresden.

The Deutsche Telekom Chair of Communication Networks is located in the Barkhausen building on the main campus of the TU Dresden. We will provide you with a well-equipped workplace there. The chair provides expertise in communication infrastructure, especially for a possible integration of bio-computing platforms.

The NCT Dresden is located at the medical campus of TU Dresden and focuses on machine learning for cancer therapy, mainly by analyzing data along the surgical treatment path to improve patient outcomes. Within this BioAI project, the NCT will support finding suitable medical applications of bio-computing for AI.

The Chair of Scientific Computing for Systems Biology combines expertise from computer science, mathematics, engineering, physics, and biology. This combination allows innovative solutions involving expertise from multiple disciplines to exploit conceptual links between seemingly disconnected disciplines.

SECAI offers a first-class environment for advancing your career. You can work with internationally renowned researchers and benefit from the school’s strong networks in industry and research. The graduation of highly qualified researchers is a central project goal in SECAI and doctoral students receive strong support for their professional and personal development.

Prerequisites

• Master’s Degree (or equivalent) in computer science, mathematics, electrical engineering or related fields of expertise
• Very good programming skills (e.g., C++, Python)
• Excellent skills and practical experience in one or more of the following research areas is beneficial:
  • Machine learning
  • Neural networks
• Ability to collaborate well in an interdisciplinary environment
• Fluency in English