REU Site: Deep Learning for Dynamical Systems in Biological and Physical Sciences

About This Grant

This REU site at the University of Southern Mississippi will prepare undergraduate students for the STEM workforce by immersing them in cutting-edge applications of deep learning to biological and physical dynamical systems. The program aims to foster a student-researcher cohort equipped with skills critical to America's competitiveness in emerging technologies. Through intensive mentorship and collaborative problem-solving, participants will bridge "Mathematics + Deep Learning" with real-world challenges in epidemiology, biophysics, and astrophysics. Over three summers, the program will engage ten students annually in an eight-week experience that will cultivate technical expertise and professional skills that propel students toward graduate studies and careers in AI-driven fields. The training component of this REU Sites program will be anchored in a Python bootcamp, coupled with hands-on workshops in various neural network architectures (e.g. feedforward, convolutional, recurrent, and transformers) and mathematical modeling. Participants will apply these techniques to model complex systems, such as infectious disease spread, neural signal dynamics, ion channel behavior and celestial mechanics. Research combining deep learning with dynamical systems involves designing neural network architectures, solving nonlinear ODE systems, collecting necessary data, and training models. Mentorship, teamwork, and professional development through daily consultations, weekly presentations, and workshops will be emphasized. The program will culminate in conference-style oral and poster presentations that showcase innovative computational approaches. By bridging deep learning with dynamical systems, this initiative will advance education and research in applied mathematics and artificial intelligence, delivering knowledge and skills participants need to address complex real-world problems. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.