Joe X
- Research Program Mentor
PhD at University of Minnesota - Twin Cities
Expertise
AI, machine learning, deep learning, data science, natural language processing, signal processing, image processing, computational modeling, biophysical modeling, statistics, biomedical engineering, medical devices, neuromodulation, movement disorders
Bio
My main research interests are in Artificial Intelligence (AI) and Biomedical Engineering. I have a B.S. (UC Berkeley) in Bioengineering, M.S. (UIUC) in Computer Science (Data Science), and Ph.D. (U Minnesota) in Biomedical Engineering. My Ph.D. research was in the area of neuromodulation (modulation of the nervous system using external stimuli), focused on understanding and improving deep brain stimulation therapy via computational modeling and neural signal processing. I began my professional career as an algorithms scientist in the medical device industry (Medtronic, Starkey Hearing Technologies), working on applications such as seizure detection, closed-loop brain stimulation, respiratory anomaly detection and health-wellness tracking. Later, I pivoted my career into the AI and Data Science spaces (General Mills, Target, UnitedHealth Group) and worked on applications such as demand forecasting, algorithmic commodities trading, recommender systems, and AI-driven solutions in healthcare. My experiences exposed me to a variety of disciplines, including: statistics, machine learning, signal processing, natural language processing, control systems, computational modeling, neuroscience, and many more. My passion is to learn. Outside of time with my family, I am either pursuing a graduate degree, collaborating on academic research, or learning a new subject online. For leisure, I enjoy reading and writing.Project ideas
Build a Recommender System
Do you ever wonder how online retailers or streaming services know just what "you may also like" based on your browsing history? The secret is something called a "recommender system"! Let's find out how it works by building one from scratch using open source data. We can further explore state-of-the-art methods in this domain.
Explore Biological vs. Artificial Neurons
Deep learning (DL) is one of the hottest topics today in the field of artificial intelligence. At its core, DL uses "artificial neural networks" to learn complex nonlinear functions from data. The building blocks of these networks are 'artificial neurons', which are computational entities that mimic the functioning of biological neurons. But just how similar (or different) is the artificial neuron to the real biological neuron? Let's find out by building (coding) a biophysical neuron model and an artificial neuron. Doing so will help one understand the inner workings of both entities and how they relate to and differ from one another.
Build a Seizure Detection Algorithm
Interested in learning about the application of machine learning in medicine? Let's build a seizure detection algorithm using open source neural data and statement of the art machine learning algorithm. In this project, you can learn about neuroanatomy, neurophysiology of epilepsy, signal processing, and machine learning.