Murat Dundar Ph.D.

Associate Professor, Computer Science

Education

  • BS - Electrical & Electronics Engineering Bogazici University Istanbul Turkey 1997
  • MS - Electrical & Computer Engineering Purdue University West Lafayette Indiana 1999
  • PhD - Electrical & Computer Engineering Purdue University West Lafayette Indiana 2003

Awards & Honors

  • 2013 CAREER Award, “Self-adjusting Models as a New Direction in Machine Learning”, awarded by the National Science Foundation 
  • 2010 Best Scientific Paper Award in Biomedical and Bioinformatics Applications Track, International Conference on Pattern Recognition (ICPR’10), awarded by International Association of Pattern Recognition
  • 2009 Data Mining Practice Prize, “Mining Medical Images”, awarded by ACM SIGKDD

Dr. Dundar received his BS degree from Bogazici University, Istanbul, Turkey, in 1997 and MS and PhD degrees from Purdue University, West Lafayette, IN, USA, in 1999 and 2003 respectively, all in Electrical Engineering. Between 2003 and 2008 he was with the CAD and Knowledge Solutions group of Siemens Health. At Siemens Health, he was involved in the development of a broad spectrum of computer aided diagnosis/detection applications including FDA-approved Lung and Colon CAD products currently deployed in thousands of hospitals around the globe. He has joined IUPUI Computer and Information Science Department as a tenure-track assistant professor in 2008, where he became an associate professor in 2014. Dr. Dundar has over fifty peer-reviewed publications covering areas of machine learning, data mining, hyperspectral imaging, computer-aided diagnosis, flow cytometry data analysis, bioinformatics, and information retrieval. His work so far have received over 1400 citations. Dr. Dundar and his colleagues at Siemens Health have received the Data Mining Practice Prize awarded by ACM SIGKDD for their work on medical image mining in 2009. Dr. Dundar has also received the National Science Foundation’s prestigious CAREER award for his work on self-adjusting machine learning in 2013. 

Current Research

Dr. Dundar’s area of expertise is in machine learning with a special focus on self-adjusting models and inference, where the traditional brute-force approach of fitting a fixed model onto the data is replaced with more flexible models that can account for the non-stationary nature of real-world machine learning problems by dynamically updating data model to better accommodate prospective data in offline as well as online settings. This is achieved by placing suitably chosen non-parametric Bayesian priors over class distributions to model not only observed classes but unobserved ones as well in an effort to perform joint classification and clustering. Scalable online and offline stochastic inference for non-parametric Bayesian models that can potentially enable self-adjusting machine learning has been at the center of Dr. Dundar’s most recent research efforts. Dr. Dundar’s research has been motivated by applications from the fields of hyperspectral imaging, computer-aided diagnosis, bioinformatics and flow cytometry data analysis, and information retrieval. 

Machine Learning Predicts Leukemia Remission with 100% Accuracy

Select Publications

  • Complete list of publications can be accessed from Dr. Dundar’s Google Scholar profile: https://goo.gl/2P7rO6
  • Murat Dundar, Ferit Akova, Yuan Qi, Bartek Rajwa, “Bayesian Nonexhaustive Learning for Online Discovery and Modeling of Emerging Classes,” In John Langford and Joelle Pineau (Eds.), Proceedings of the 29th International Conference on Machine Learning (ICML'12), Edinburgh, Scotland, June 26-July 1, 2012 (pp. 113-120). Omnipress, 2012.
  • Murat Dundar, Sunil Badve, Gokhan Bilgin, Vikas Raykar, Olcay Sertel, Metin N. Gurcan, “Computerized Classification of Intraductal Breast Lesions using Histopathological Images”, IEEE Transactions on Biomedical Engineering, 58(7):1977-1984, 2011.
  • Ferit Akova, Murat Dundar, V. Jo Davisson, E. Daniel Hirleman, Arun K. Bhunia, J. Paul Robinson, Bartek Rajwa, “A Machine-learning Approach for Label-free Detection of Unmatched Bacterial Serovars”, Statistical Analysis and Data Mining Journal, 3(5):289-301, 2010.
  • Murat Dundar, Matthias Wolf, Sarang Lakare, Marcos Salganicoff, Vikas Raykar “Polyhedral Classifiers for Target Detection: A Case Study: Colorectal Cancer”, In Proceedings of the 25th International Conference on Machine Learning (ICML 2008), pp.288-295, Helsinki, July 2008.
  • Murat Dundar, Jinbo Bi, “Joint optimization of cascaded classifiers for computer aided detection”, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR ‘07),  Minneapolis, Minnesota, USA, 18-23 June 2007. IEEE Computer Society 2007.  (Oral paper, acceptance rate: 5%)
  • Murat Dundar, Balaji Krishnapuram, Jinbo Bi, Bharat Rao, “Learning from Non-IID Data”, In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007), Hyderabad, India, January 6-12, 2007.