18Apr

Title:
Colloquium: Thomas Ploetz (Georgia Tech)

Description: 

Title: Apply It! Machine Learning for Real World Applications / Real World Applications for Machine Learning -- The Case of Digital Health.


Speaker: Thomas Ploetz


Location: UTA 5.522 (1616 Guadalupe St., 5th Floor)


Abstract:


Machine Learning has become a major research field and substantial progress has been made on solutions to many fundamental problems related to deriving parametric models from data and using such models for data analysis tasks. However, the importance of real world applications of machine learning methods specifically for sensor data analysis "in the wild", that is in naturalistic environments and targeting real-life problems, is still underappreciated. Vice versa the prevalent "utilitarian" use of machine learning methods for real-world applications, effectively treating them as a "black box", is dangerous at least as it can lead to flawed results due to inappropriate use of the methods. There is a growing need to bridge the gap between core method development and practitioners' use of machine learning techniques.


In this talk I will explore the nexus between core method development and real world applications of machine learning techniques, specifically how applications can push the boundaries of machine learning research and vice versa. The focus of this exploration will be on health and wellbeing, specifically on projects I have been working on that focus on computational behaviour analysis. Using wearable and ubiquitous sensors behaviour is captured opportunistically in naturalistic environments and bespoke machine learning methods have been developed for the assessment of behaviour data in health and wellbeing scenarios. I will illustrate how such real-world applications have allowed me and my team to push the boundaries of core sensor data analysis research, and -- vice versa -- how machine learning research influences real world applications. With a specific view on the ubiquitous computing (Ubicomp) as well as on the wider human computer interaction (HCI) research communities my work is motivated by the desire to bridge the gap between practitioners (health professionals as well as patients), Ubicomp and HCI researchers, as well as core methods developers (machine learning researchers). Through a deeply interdisciplinary approach my team and I are aiming for developing systems that have a positive impact in real-world scenarios.


Bio:


Thomas Ploetz is a Computer Scientist with expertise and almost 15 years experience in Pattern Recognition and Machine Learning research (PhD from Bielefeld University, Germany). His research agenda focuses on applied machine learning, that is developing systems and innovative sensor data analysis methods for real world applications. Primary application domain for his work is computational behaviour analysis where he develops methods for automated and objective behaviour assessments in naturalistic environments. Main driving functions for his work are "in the wild" deployments and as such the development of systems and methods that have a real impact on people's lives.


Thomas has recently (2017) joined the School of Interactive Computing at the Georgia Institute of Technology in Atlanta, USA where he works as an Associate Professor of Computing. Prior to this he was an academic at the School of Computing Science at Newcastle University in Newcastle upon Tyne, UK, where he was a Reader (Assoc. Prof.) for "Computational Behaviour Analysis" affiliated with Open Lab, Newcastle's interdisciplinary research centre for cross-disciplinary research in digital technologies.


Homepage: http://www.ncl.ac.uk/computing/people/profile/thomasploetz.html#background


Location: 
5.522

Time:
1:15pm to 2:30pm

Year:
2017

glqxz9283 sfy39587stf02 mnesdcuix8
sfy39587stf03
sfy39587stp14