Have a UROP opening you would like to submit?
Please fill out the form.
Physics Informed Neural Network for Image Sensors
2: Mechanical Engineering
In the last decades, deep learning has achieved enormous progress in various tasks in computer science, including computer vision and natural language processing. Recent work on physics informed neural network has shown that imposing physical governing equations as regularization can strongly improve the generalization of neural networks. The approach requires implementing the governing equations into deep learning frameworks. The main goal of this project is to apply physics informed neural network for image-based flame diagnostics. Students will help implement physics laws into deep learning frameworks of PyTorch/Julia.
Experience with Python/Julia and machine learning is required. Experience with deep learning in Tensorflow/Pytorch/Julia is preferred but not required. Exposure to differential equations, optimization, and numerical simulation is helpful but not required.