Dr. Lu brings expertise in machine learning, particularly integrating human knowledge into machine learning and explainable machine learning. He has applied machine learning in a range of domain applications, such as autonomous driving and machine learning for optimized design and control of energy storage systems.
My research is focused on the human biometric data (such as motion) to guide the design and manufacturing of assistive and proactive devices. Embedded and external sensors generate ample data which require scientific approaches to analyze and create knowledge. I have worked closely with the University of Michigan Orthotics and Prosthetics Center in the design and manufacturing of custom assistive devices using 3D-printing and cyber-based design. The goal is to create a cyber-physical system that can acquire the data from scanning, sensors, human motion, user feedback, clinician diagnosis into quantitative health metrics and guidelines to improve the quality of care for people with needs.
Dr. Arpan Kusari has joined UMTRI as an Assistant Research Scientist, a position where he will bring his cutting-edge industry experience. Dr. Kusari has spent five years at Ford Motor Company researching exclusively on making autonomous vehicles safe and viable, working collaboratively with researchers from MIT and University of Michigan to advance the state-of-the-art knowledge in autonomous vehicles. His research interest spans through the spheres of sensing and perception; and decision-making and control, in the domain of autonomous vehicles. In the sensing and perception realm, his interests lie in uncertainty quantification and fault tolerance of a generic sensor suite. Dr. Kusari is also interested in utilizing noise reduction methods for designing cost-effective low SNR (signal-to-noise ratio) LiDARS. In decision making and control, he is focused on creating a robust framework capable of handling the uncertainty stemming from other road users’ behavior. In that regard, Dr. Kusari is pursuing development of methods for increasing the efficiency and robustness of probabilistic formalisms such as reinforcement learning and evolutionary algorithms to safely navigate the dynamic environment. His doctoral research was in LiDAR mapping in the areas of sensor calibration, precise estimation of earthquake displacement and uncertainty quantification in the point cloud.
Our team develops machine learning algorithms for the enhancement of outcomes in cataract surgery, the most commonly performed surgery in the world. Our works focuses on developing models for postoperative refraction after cataract surgery and analysis of surgical quality.
My research is at the intersection of neuroscience and artificial intelligence. My group uses neuroscience or brain-inspired principles to design models and algorithms for computer vision and language processing. In turn, we uses neural network models to test hypotheses in neuroscience and explain or predict human perception and behaviors. My group also develops and uses machine learning algorithms to improve the acquisition and analysis of medical images, including functional magnetic resonance imaging of the brain and magnetic resonance imaging of the gut.
We use brain-inspired neural networks models to predict and decode brain activity in humans processing information from naturalistic audiovisual stimuli.
My research interests are in the areas of brain-inspired machine intelligence and its applications such as mobile robots and autonomous vehicles. To achieve true machine intelligence, I have taken two different approaches: bottom-up data-driven and top-down theory-driven approach. For the bottom-up data-driven approach, I have investigated the neuronal structure of the brain to understand its function. The development of a high-throughput and high-resolution 3D tissue scanner was a keystone of this approach. This tissue scanner has a 3D virtual microscope that allows us to investigate the neuronal structure of a whole mammalian brain in a high resolution. The top-down theory-driven approach is to study what true machine intelligence is and how it can be implemented. True intelligence cannot be investigated without embracing the theory-driven approach such as self-awareness, embodiment, consciousness, and computational modeling. I have studied the internal dynamics of a neural system to investigate the self-awareness of a machine and model neural signal delay compensation. These two meet in the middle where machine intelligence is implemented for mechanical systems such as mobile robots and autonomous vehicles. I have a strong desire to bridge the bottom-up and top-down approaches that lead me to conduct research focusing on mobile robotics and autonomous vehicles to combine the data-driven and theory-driven approaches.
Kentaro Toyama is W. K. Kellogg Professor of Community Information at the University of Michigan School of Information and a fellow of the Dalai Lama Center for Ethics and Transformative Values at MIT. He is the author of “Geek Heresy: Rescuing Social Change from the Cult of Technology.” Toyama conducts interdisciplinary research to understand how the world’s low-income communities interact with digital technology and to invent new ways for technology to support their socio-economic development, including computer simulations of complex systems for policy-making. Previously, Toyama did research in artificial intelligence, computer vision, and human-computer interaction at Microsoft and taught mathematics at Ashesi University in Ghana.
Dr. Jin Lu is an Assistant Professor of Computer and Information Science at the University of Michigan, Dearborn.
His major research interests include machine learning, data mining, optimization, matrix analysis, biomedical informatics, and health informatics. Two main directions are being pursued:
(1) Large-scale machine learning problems with data heterogeneity. Data heterogeneity is common across many high-impact application domains, ranging from recommendation system to Computer Vision, Bioinformatics and Health-informatics. Such heterogeneity can be present in a variety of forms, including (a) sample heterogeneity, where multiple resources of data samples are available as side information; (b) task heterogeneity, where multiple related learning tasks can be jointly learned to improve the overall performance; (c) view heterogeneity, where complementary information is available from various sources. My research interests focus on building efficient machine learning methods from such data heterogeneity, aiming to improve the learning model by making the best use of all data resources.
(2) Machine learning methods with provable guarantees. Machine learning has been substantially developed and has demonstrated great success in various domains. Despite its practical success, many of the applications involve solving NP-hard problems based on heuristics. It is challenging to analyze whether a heuristic scheme has any theoretical guarantee. My research interest is to employ granular data structure, e.g. sample clusters or features describing an aspect of the sample, to design new theoretically-sound models and algorithms for machine learning problems.
David works on computer vision and machine learning with the end goal of developing autonomous systems that can learn to build representations of the underlying state and dynamics of the world through observation (and potentially interaction).
Towards this end, he is particularly interested in understanding physical and functional properties from images. His research interest in physical properties aims to address how we can recover a rich 3D world from a 2D image. He is especially interested in representations — the answers that are obvious are also obviously defective — as well as how we should reconcile our strong prior knowledge about this structure of the problem with data-driven techniques. In recent work, he has become interested in applying this more broadly in the hope that we can develop AI systems that can learn how the physical world works from observation, including work on solar physics. In functional properties, he is interested in inferring and understanding opportunities for interaction with the environment by both robots and humans, both in terms of how one would learn this and what this implies for a physical understanding of the world.
Current research includes a project funded by Toyota that uses Markov Models and Machine Learning to predict heart arrhythmia, an NSF-funded project to detect Acute Respiratory Distress Syndrome (ARDS) from x-ray images and projects using tensor analysis on health care data (funded by the Department of Defense and National Science Foundation).