Department of Mathematics

Time and Place: Tuesdays 3:05-4:20 pm in Room 0231, Love Building

Course: MAP 6939

Scope: The Applied and Computational Math Seminar is series of talks with various topics covering a broad spectrum of not only applied and computational mathematics but also engineering. Researchers outside of the Department of Mathematics and Florida State University, postdocs and senior Ph.D students are also welcomed to share their work. Please contact the organizer if you wish to schedule your talk. For Spring 2023, contact Kyle Gallivan (gallivan"at"math.fsu.edu)

Abstract: Among the numerous advances taking place within the discipline of machine learning, the sub-field currently known as scientific machine learning has seen encouraging developments. This branch of ML research includes topics such as Physics Informed Neural Networks (PINNs), Neural Ordinary Differential Equations (Neural ODEs), Universal Ordinary Differential Equations (Universal ODEs), Sparse Identification of Nonlinear Dynamics (SINDy), and more. These tools have demonstrated an ability to advance numerical results within various scientific computing applications. This talk will introduce Neural ODEs and explore a particular application within the field of cognitive psychology. The Triangle model is a prominent theory of word reading based on principles of the connectionist or parallel distributed processing (PDP) framework. Computational implementations of the model have simulated various aspects of reading, including aspects of skilled adult reading, reading acquisition in typically developing and learning-disabled children, acquired dyslexia, and reading across languages. Through a partnership with the Haskins Laboratory, we have implemented the Triangle model using modern machine learning frameworks and leveraging the advances in neural ode techniques. 

Bio: Dr. Nathan Crock is an affiliate faculty member in the Department of Scientific Computing and the new Interdisciplinary Data Science Program at Florida State University. He is a member of the Computational Intelligence Lab at FSU and directs the machine learning and artificial intelligence research efforts at NewSci Labs, where he focuses on developing AI that benefits the public and social sectors. He is a reviewer for the Frontiers in Neuroinformatics journal and an ambassador for DeepLearning.ai, for which he organizes Tallahassee’s Deep Learning meetups. Recently, he co-founded a speech-to-speech AI platform-as-a-service company called Call Simulator Inc. Before his positions here in Tallahassee, Nathan was a visiting scholar at the Max Planck Florida Institute for Neuroscience in Jupiter, Florida, a computer vision consultant for the Intelligent Robotics Group at NASA AMES and a Data Science instructor at Zipfian Academy in San Francisco, California.