Modern real-time scheduling theory was started by Professor David Liu at UIUC with his seminal paper Scheduling Algorithms for Multiprogramming in a Hard Real-Time Environment. Built upon this pioneering work, Professor Lui Sha and his collaborators created the modern real-time scheduling theory that transformed the real-time computing standards and impacted many national high technology projects.
New Physics Model Guided Machine Learning: A physics model is a validated low-dimensional model of causality with critical properties such as provable stability in control applications. DNN is a high-dimensional model of correlations that may capture not only unmodeled dynamics overlooked by physics model but also spurious corrections in the training samples (overfitting). As a result, while DNN has statistically significant performance improvement, but it may also generate outputs inconsistent with the laws of physics that could lead to catastrophic failures. Physics Model Edited DNN combines the best of the physical model and DNN model.
Traditionally, we project a higher dimensional space to a lower dimension space for computational efficiency at the cost of performance. Physics model-based neuron editing turns this conventional projection approach upside down. We project a lower dimensional physics model onto a higher dimensional DNN model by 1) augmenting the input feature vector with physic variables and 2) removing relations permitted by DNN but contradicting the laws physics. The physics model edited DNN is constrained by physical laws. We gain control-performance at the cost of computing. To ensure stability of control in spite of DNN software failures, we use Simplex architecture to ensure that the states under the control of the edited DNN must remain within the stability envelope of the physical model based control.
Positions Available: One Postdoc and part-time jobs in the lab: software development and/or hardware devices for research.
Other Current Projects