Our focus is on methods, systems and frameworks that enable the engineering of safe-AI systems that are context-sensitive, provide explainability of achieved results, and whose architectural complexity scales with the complexity of the context, task and accuracy requirements. We believe that this requires a synthesis of the best practices in modern machine learning practice with classical systems engineering methods. Synthesizing the next generation platforms and tools to realize safe-AI products and solutions will necessitate the organization and formalization the space of (contexts, tasks, performance requirements) (i.e. (C,T,P)) and how they map to (programs and parameters). We seek answers to specific questions such as: What is the space of intelligent tasks?, In what specific contexts are these intelligent tasks to be performed and with what specific performance requirements in terms of accuracy, robustness, and computational efficiency? What are the appropriate representations for contextual models? Is there a design theory for how these model representations along with task and performance requirements map to programs?, i.e. What are the design patterns for cognitive solutions (programs) to address given (C, T, P) choices? While our application focus over the years has been largely computer vision, we envision that our methodology and framework will scale to other domains. Thus, we collaborate with other professors to focus on multi-modal systems involving vision, acoustics/speech, language and other modalities.
Topics for theses include both theory and practical applications, but are not limited to:
- Fusion of modern Machine Learning, Bayesian Models and Inference, Artificial intelligence principles for design of Safe, Inspectable, Explainable Cognitive Systems
- Applications – Cognitive Systems and applications in Mobility, Logistics, Healthcare, Industrial automation, Energy, Safety and Security.
- Performance characterization of cognitive systems
Current Phd Students and Topics:
SUBBU VEERASAVARAPPU: Goethe University, Phd. Topic: “Simulation for Cognitive Vision”.
TOBIAS WEIS: Goethe University, Phd. Topic: “Memory Representations for Cognitive Vision”.
RUDRA HOTA: Goethe University, Phd. Topic: “Hypotheses Generators for Cognitive Vision”.
MARTIN MUNDT: Phd. Topic: “Meta-learning and Continuous learning”
PHD Students (as primary Industrial advisor at Siemens):
JAN ERNST: University of Erlangen (2013), Phd. Topic: “The Trace Model for Spatial Invariance with Applications to Structured Pattern Recognition, Image Patch Matching and Incremental Visual Tracking”.
TONY HAN: University of Illinois and Urbana-Champaign (2007), Phd. Topic: “Watching Humans and their Activities”.
BINGLONG XIE: Lehigh University (2006), Phd. Topic: “Statistical Methods for Face Detection and Recognition”.
WEI-LIANG LI: Lehigh University (2005), Phd. Topic: “Performance Characterization of Boosting in Computer Vision”.
YANGHAI TSIN: Carnegie Mellon University (2003), Phd. Topic: “Kernel Correlation as an Affinity Measure in Point-Sampled Vision Problems”.
XIANG GAO: Lehigh University (2003), Phd. Topic: “Statistical Modeling and Performance Characterization of Low Level Vision Algorithms”.
MICHAEL GREIFFENHAGEN: University of Erlangen (2002), Phd. Topic: “Statistical Modeling and Performance Characterization of a Real-time Dual Camera Surveillance”.
ZHAO-HUI SUN: University of Rochester (2001), Phd. Topic: “Object-Based Video Processing with Depth”
Masters and Bachelor theses completed:
DIANA MANSUROVA, Goethe Universität, (2018) Topic: `Activity Monitoring for Automotive Applications.
HENDRIK WEICHULA: Goethe Universität (2018), Topic: “Evaluation of Machine Learning Services”.
ANDRES F. RODRIGUEZ: Goethe Universität (2017), Topic: “Music Classification using Machine Learning”.
SILVIA WALK: Goethe Universität (2017), Topic: “Statistical Characterization of Program Behavior”.
LISA HORNUNG: Goethe Universität (2017), Topic: “Deep Learning for Brake-light Detection”.
ANNA-LENA FINK: Goethe Universität (2016), Topic: “Natural Language Processing for Model based System Design”.
TIMM HESS: Goethe Universität (2016), Topic: “Simulation for Deep Learning (RoboSoccer)”.
SINA DITZEL: Goethe Universität (2016), Topic: “Robot-Localization using Particle Filters”.
MARIUSZ MAZUREK: Goethe Universität (2015), Topic: “Symmetry in Computer Vision”.
ALI SHAHID: Goethe Universität (2015), Topic: “3D Motion Data Fusion: IR-SCT, Nexonar Ultrasound“.
ALEXANDER HEUN: Goethe Universität (2015), Topic: “Object Recognition in the Automotive Domain’’.
RICHARD ADAMCA: Goethe Universität (2014), Topic: “Video Pre-Processing for Layer Separation”.
PATTREEYA TANISARO: Goethe Universität (2012), Topic: “Extraction of structural components and patterns from relational representation of road scenes”.
Masters theses (In industry at Siemens):
KATJA SAKIEWICZ: Technical University of Hamburg-Harburg (1998), Topic: “Action Recognition from Tennis Video”.
BJOERN STENGER: University of Bonn (2001), Topic: “Topology-Free Hidden Markov Models with Applications in Video Surveillance”.
CLAUDIA SCHLOSSER: University of Passau (2005), Topic: “Performance Characterization of Mean-Shift”.