Machine learning is widely used for optimizing modern digital systems, addressing our inability to model these systems from first principles due to their complexity and the high dimensional data they generate. However, machine learning models, such as neural networks, often contain millions of parameters, making it difficult to understand their behavior and to trust their output. Moreover, they require large amounts of labeled data, which is not always available. There are machine learning approaches targeting these challenges (e.g. surrogate modeling or unsupervised learning), but they are often limited in their application. Symbolic AI approaches, on the other hand, are often explainable and can leverage expert knowledge to deal with few labeled samples, but struggle with noisy and high dimensional data.
This position is funded by the AIMS5.0 European project aiming to develop AI-enabled hardware and software components and systems across the whole industrial value chain to increase the overall efficiency and sustainability. The project has 53 industrial and academic partners. The role of the TUE is to develop AI enabled holistic planning and scheduling methods that will adapt to the current and anticipated state of the manufacturing processes and the supply chain. The use cases of our industrial partners include adapting the product specification to the available resources, adapting planning of manufacturing processes to bottlenecks along the supply chain, optimizing the manufacturing processes for low batch sizes of custom products, and improving traceability and root cause analysis in incident management.
The TUE is participating with the Computer Science and the Industrial Engineering departments, with 3 PhD and 1 Postdoc position. This Postdoc position is at the Computer Science department. We are looking for candidates that would like to join our team exploring how to combine machine learning methods (for extracting information from structured and high-dimensional data from the manufacturing systems and the supply chain) and symbolic AI methods (for reasoning with the
extracted information and expert knowledge provided by the industrial partners by means of knowledge graphs) to address various planning, scheduling and optimization problems in complex industrial systems.
The successful candidate for this position is expected to:
- Contribute to performing scientific research on integrated symbolic AI and machine learning in general, and to validate the results in the AIMS5.0 project.
- Contribute to publishing results at (international) conferences and journals.
- Collaborate with the other PhD and Postdoc researchers in this project.
- Collaborate with other group and faculty members.
- Collaborate with selected AIMS5.0 project partners, attend project meetings and contribute to deliverables and project outcome.
- Assist with educational tasks (e.g. support lab/course assignments and/or supervise (under)graduate/internships students).