In machine learning applications, practitioners must take into account the cost associated with the algorithm. These costs include: Cost of acquiring training dataCost of data annotation/labeling and cleaningComputational cost for model fitting, validation, and testingCost of collecting features/attributes for test dataCost of user feedback collect

part I|2 pages

I Theoretical Underpinnings of Cost-Sensitive Machine Learning

chapter 1|28 pages

Algorithms for Active Learning

ByBurr Settles

chapter 2|30 pages

Semi-Supervised Learning: Some Recent Advances

ByXueyuan Zhou, Ankan Saha, Vikas Sindhwani

chapter 3|26 pages

Transfer Learning, Multi-Task Learning, and Cost-Sensitive Learning

ByLearning Bin Cao, Yu Zhang, Qiang Yang

chapter 4|14 pages

Cost-Sensitive Cascades

ByVikas C. Raykar

chapter 5|56 pages

Selective Data Acquisition for Machine Learning Saar-Tsechansky

ByJosh Attenberg, Prem Melville, Foster Provost, and Maytal

part II|2 pages

II Cost-Sensitive Machine Learning Applications

chapter 6|60 pages

Minimizing Annotation Costs in Visual Category Learning

BySudheendra Vijayanarasimhan, Kristen Grauman

chapter 7|22 pages

Reliability and Redundancy: Reducing Error Cost in Medical Imaging

ByXiang Sean Zhou, Yiqiang Zhan, Zhigang Peng, Maneesh Dewan, Bing Jian, Arun Krishnan, Martin Harder, Raphael Schwarz, Lars Lauer, Heiko Meyer, Stefan Grosskopf, Ute Feuerlein, Hendrik Ditt

chapter 8|24 pages

Cost-Sensitive Learning in Computational Advertising

ByDeepak Agarwal

chapter 9|33 pages

Cost-Sensitive Machine Learning for Information Retrieval

ByMartin Szummer, Filip Radlinski