Artificial intelligence and machine learning, particularly in its latest incarnation of deep learning, can act as a powerful amplifying factor for almost any application or research topic. However, in order to apply these tools with the maximum benefit, you need to make sure that your research problem is formulated in a way that it can take advantage of the strengths of these tools. Basically, you need to partition your problem between what is subject of your research contribution and what you can ``leave to learning''.
In this talk, I will discuss my experience in applying AI and deep learning in the field of sensor networks, robotics and a healthcare application. I will talk about taking the agent perspective, reward design, end-to-end learning and the segmentation of learned versus engineered components.
Lotzi Boloni is a Professor of Computer Science at the University of Central Florida (with a secondary joint appointment in the Dept. of Electrical and Computer Engineering). He received a PhD and MSc degree from the Computer Sciences Department of Purdue University and BSc in Computer Engineering from the Technical University of Cluj-Napoca, Romania. His research interests include artificial intelligence, autonomous agents, deep learning and robotics. He is continuously looking for ways to apply AI techniques in practical applications.