Research Assistant –
Salary grade TV-L E13 (BW) –
PhD Position in Generative Models for Chemical Engineering
The AI for materials science (AiMat) research group at KIT is searching for a new PhD student to work on generative machine learning models for applications in chemical engineering. Do you have significant experience in machine learning and generative models? Do you want to extend your knowledge to other fields of expertise in an interdisciplinary setting? Would you like to see how your research makes an impact on real-world applications? Yes? Then apply now for a PhD position in the AIMat research group at KIT!
Contact person: T.T.-Prof. Dr. Pascal Friederich (email@example.com)
Research Assistant –
Salary grade TV-L E13 –
KnowTD: Translation of thermodynamic knowledge to computers
We are looking for a highly motivated research assistant to pursue a PhD project within the Priority Program 2331 “Machine Learning in Process Engineering: Knowledge Meets Data: Interpretability, Extrapolation, Reliability, Trust” of the German Research Foundation (DFG). The work will be carried out at the Laboratory of Engineering Thermodynamics (LTD) at TU Kaiserslautern, in an inspiring interdisciplinary research environment.
The project addresses one of the fundamental problems of artificial intelligence: the translation of human knowledge to computers. Our goal is to achieve this for the extensive and deep knowledge of thermodynamics. In preliminary work, we have developed a feasible way to do this, in which the thermodynamic knowledge is represented by interacting graphs. However, we do not limit ourselves to the representation of knowledge, the system to be developed, KnowTD, will be able to build thermodynamic models of real-world objects, analyze them and answer questions about their thermodynamic behavior. Thus, thermodynamic knowledge will become operable on the computer, with and possibly without interaction with humans.
The project will be carried out in close co-operation with two groups from computer science department of TU Kaiserslautern, who will not only participate in the code development but also supply a linguistic input/output for KnowTD based on deep learning techniques.
Contact person: Prof. Dr.-Ing. Hans Hasse (firstname.lastname@example.org)