Balaji Krishnapuram is a senior R&D manager at Siemens Medical Solutions. He earned a Ph.D. in electrical and computer engineering from Duke University. His research interests include statistical data mining and information retrieval.
Shipeng Yu is a senior staff scientist at Siemens Medical Solutions. He earned a Ph.D. in computer science from the University of Munich. His research interests include statistical machine learning, data mining, Bayesian analysis, information retrieval and extraction, healthcare analytics, and personalized medicine.
R. Bharat Rao is senior director and head of Knowledge Solutions at Siemens Medical Solutions, where was recognized as one of its Inventors of the Year in 2005. He also received the 2011 ACM SIGKDD Lifetime Service Award for pioneering applications of data mining for healthcare. He earned a Ph.D. in electrical and computer engineering from the University of Illinois at Urbana-Champaign. His research interests include machine learning, healthcare analytics, mining large data, and personalized medicine.
In machine learning applications, practitioners must take into account the cost associated with the algorithm. These costs include:
- Cost of acquiring training data
- Cost of data annotation/labeling and cleaning
- Computational cost for model fitting, validation, and testing
- Cost of collecting features/attributes for test data
- Cost of user feedback collection
- Cost of incorrect prediction/classification
Cost-Sensitive Machine Learning is one of the first books to provide an overview of the current research efforts and problems in this area. It discusses real-world applications that incorporate the cost of learning into the modeling process.
The first part of the book presents the theoretical underpinnings of cost-sensitive machine learning. It describes well-established machine learning approaches for reducing data acquisition costs during training as well as approaches for reducing costs when systems must make predictions for new samples. The second part covers real-world applications that effectively trade off different types of costs. These applications not only use traditional machine learning approaches, but they also incorporate cutting-edge research that advances beyond the constraining assumptions by analyzing the application needs from first principles.
Spurring further research on several open problems, this volume highlights the often implicit assumptions in machine learning techniques that were not fully understood in the past. The book also illustrates the commercial importance of cost-sensitive machine learning through its coverage of the rapid application developments made by leading companies and academic research labs.
THEORECTICAL UNDERPINNINGS OF COST-SENSTIVE MACHINE LEARNING: Algorithms for Active Learning. Semi-Supervised Learning: Some Recent Advances. Transfer Learning, Multi-Task Learning, and Cost-Sensitive Learning. Cost-Sensitive Cascades. Selective Data Acquisition for Machine Learning. COST-SENSITIVE MACHINE LEARNING APPLICATIONS: Minimizing Annotation Costs in Visual Category Learning. Reliability and Redundancy: Reducing Error Cost in Medical Imaging. Cost-Sensitive Learning in Computational Advertising. Cost-Sensitive Machine Learning for Information Retrieval. Index.
This volume is one of the first books to provide an overview of the current research efforts and problems in this area. It discusses real-world applications that incorporate the cost of learning into the modeling process. The first part of the book describes well-established machine learning approaches for reducing data acquisition costs during training as well as approaches for reducing costs when systems must make predictions for new samples. The second part covers real-world applications, such as computer-aided medical diagnosis, that effectively trade off different types of costs.
Über den Autor
Balaji Krishnapuram is a senior R&D manager at Siemens Medical Solutions. He earned a Ph.D. in electrical and computer engineering from Duke University. His research interests include statistical data mining and information retrieval. Shipeng Yu is a senior staff scientist at Siemens Medical Solutions. He earned a Ph.D. in computer science from the University of Munich. His research interests include statistical machine learning, data mining, Bayesian analysis, information retrieval and extraction, healthcare analytics, and personalized medicine. R. Bharat Rao is senior director and head of Knowledge Solutions at Siemens Medical Solutions, where was recognized as one of its Inventors of the Year in 2005. He also received the 2011 ACM SIGKDD Lifetime Service Award for pioneering applications of data mining for healthcare. He earned a Ph.D. in electrical and computer engineering from the University of Illinois at Urbana-Champaign. His research interests include machine learning, healthcare analytics, mining large data, and personalized medicine.
Inhaltsverzeichnis
THEORECTICAL UNDERPINNINGS OF COST-SENSTIVE MACHINE LEARNING Algorithms for Active Learning, Burr Settles Query Strategy Frameworks A Unified View Summary and Outlook Semi-Supervised Learning: Some Recent Advances, Xueyuan Zhou, Ankan Saha, and Vikas Sindhwani Semi-Supervised Prediction for Structured Outputs Theoretical Analysis New Directions Transfer Learning, Multi-Task Learning, and Cost-Sensitive Learning, Bin Cao, Yu Zhang, and Qiang Yang Notations Transfer Learning Models Multi-Task Learning Models Conclusion and Future Work Cost-Sensitive Cascades, Vikas C. Raykar Features Incur a Cost Cascade of Classifiers Successful Applications of Cascaded Architectures Training a Cascade of Classifiers Tradeoff between Accuracy and Cost Conclusions and Future Work Selective Data Acquisition for Machine Learning, Josh Attenberg, Prem Melville, Foster Provost, and Maytal Saar-Tsechansky Overarching Principles for Selective Data Acquisition Active Feature-Value Acquisition Labeling Features versus Examples Dealing with Noisy Acquisition Prediction Time Information Acquisition Alternative Acquisition Settings Conclusion COST-SENSITIVE MACHINE LEARNING APPLICATIONS Minimizing Annotation Costs in Visual Category Learning, Sudheendra Vijayanarasimhan and Kristen Grauman Reducing the Level of Supervision Reducing the Amount of Supervision Reducing the Effort Required in Supervision Cost-Sensitive Multi-Level Active Learning Conclusion Reliability and Redundancy: Reducing Error Cost in Medical Imaging, X.S. Zhou, Y. Zhan, Z. Peng, M. Dewan, B. Jian, A. Krishnan, M. Harder, R. Schwarz, L. Lauer, H. Meyer, S. Grosskopf, U. Feuerlein, H. Ditt, and M. Scheuering A Measure of Reliability Reliability of Pattern Localization: Asymmetric Cost for FPs and FNs Implications and Learning Strategy for Medical Imaging Applications Related Work and Discussions Cost-Sensitive Learning in Computational Advertising, Deepak Agarwal Performance Advertising: Sponsored Search and Contextual Matching Display Advertising Discussion Cost-Sensitive Machine Learning for Information Retrieval, Martin Szummer and Filip Radlinski Utility in Information Retrieval Learning to Rank Reducing Labeling Cost Multiple Utilities Conclusion Index A Bibliography appears at the end of each chapter.
Klappentext
The first comprehensive source on cost-sensitive learning, this reference focuses on various research domains in machine learning that attempt to solve cost-sensitive learning with simplifying assumptions. The book explicitly deals with tradeoffs between the various costs and benefits inherent in many domains of machine learning research, including semisupervised learning, active learning, active feature acquisition, and inductive transfer learning. It covers recently developed methods, along with several applications of cost-sensitive learning, including natural language processing, computer vision, medical applications, web ads, and marketing. Real-world applications aid with reader understanding.
