FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W163086937> ?p ?o ?g. }

• W163086937 abstract "Machine learning has become one of the most active and exciting areas of computer science research, in large part because of its wide-spread applicability to problems as diverse as natural language processing, speech recognition, spam detection, search, computer vision, gene discovery, medical diagnosis, and robotics. At the same time, the growing popularity of the Internet and social networking sites like Facebook has led to the availability of novel sources of data on the preferences, behavior, and beliefs of massive populations of users. Naturally, both researchers and engineers are eager to apply techniques from machine learning in order to aggregate and make sense of this wealth of collective information. However, traditional theories of learning fail to capture the complex issues that arise in such settings, and as a result, many of the techniques currently employed are ad hoc and not well understood. The goal of this dissertation is to narrow this gap between theory and practice. To that end, we present a series of new learning models and algorithms designed to address and illuminate problems commonly faced when aggregating local information across large population. We build on the foundations of learning theory to examine the fundamental trade-offs that arise when aggregating preference data across many similar users to learn a model of a single user's tastes. We introduce and analyze a computational theory of learning from collective behavior, in which the goal of the algorithm is to accurately model and predict the future group behavior of a large population. We develop a forecaster that is guaranteed to perform reasonably well compared to best expert in a population but simultaneously never any worse than the average. Finally, we investigate the computational complexity of pricing in prediction markets, betting markets designed to aggregate individuals' opinions about the likelihood of future events, and propose an approximation technique based on the previously unexplored connection between prediction market prices and learning from expert advice." @default.
• W163086937 created "2016-06-24" @default.
• W163086937 creator A5029730907 @default.
• W163086937 creator A5043117896 @default.
• W163086937 date "2009-01-01" @default.
• W163086937 modified "2023-10-16" @default.
• W163086937 title "Learning from collective preferences, behavior, and beliefs" @default.
• W163086937 cites W113837456 @default.
• W163086937 cites W1444520626 @default.
• W163086937 cites W1513351507 @default.
• W163086937 cites W1513468570 @default.
• W163086937 cites W1520252399 @default.
• W163086937 cites W1520903655 @default.
• W163086937 cites W1542886316 @default.
• W163086937 cites W1561513404 @default.
• W163086937 cites W1570963478 @default.
• W163086937 cites W1596394732 @default.
• W163086937 cites W1599628716 @default.
• W163086937 cites W1614597761 @default.
• W163086937 cites W1654194294 @default.
• W163086937 cites W1766619930 @default.
• W163086937 cites W177751847 @default.
• W163086937 cites W1863744984 @default.
• W163086937 cites W1897619428 @default.
• W163086937 cites W1964964840 @default.
• W163086937 cites W1972178529 @default.
• W163086937 cites W1972265965 @default.
• W163086937 cites W1986252988 @default.
• W163086937 cites W1988790447 @default.
• W163086937 cites W1990283121 @default.
• W163086937 cites W2000684188 @default.
• W163086937 cites W2005951230 @default.
• W163086937 cites W2006912660 @default.
• W163086937 cites W2019834961 @default.
• W163086937 cites W2021680564 @default.
• W163086937 cites W2034025033 @default.
• W163086937 cites W2036043322 @default.
• W163086937 cites W2041157860 @default.
• W163086937 cites W2042123098 @default.
• W163086937 cites W2044225472 @default.
• W163086937 cites W2053634345 @default.
• W163086937 cites W2055639053 @default.
• W163086937 cites W2056204623 @default.
• W163086937 cites W2056609785 @default.
• W163086937 cites W2061212083 @default.
• W163086937 cites W2065368202 @default.
• W163086937 cites W2065543353 @default.
• W163086937 cites W2072443840 @default.
• W163086937 cites W2074925781 @default.
• W163086937 cites W2075164088 @default.
• W163086937 cites W2075208090 @default.
• W163086937 cites W2078378390 @default.
• W163086937 cites W2084544490 @default.
• W163086937 cites W2086661071 @default.
• W163086937 cites W2087258353 @default.
• W163086937 cites W2089579808 @default.
• W163086937 cites W2093825590 @default.
• W163086937 cites W2095374884 @default.
• W163086937 cites W2095907808 @default.
• W163086937 cites W2095976990 @default.
• W163086937 cites W2099111195 @default.
• W163086937 cites W2099811697 @default.
• W163086937 cites W2099971677 @default.
• W163086937 cites W2103012681 @default.
• W163086937 cites W2104602264 @default.
• W163086937 cites W2105535951 @default.
• W163086937 cites W2108985320 @default.
• W163086937 cites W2110091014 @default.
• W163086937 cites W2113889316 @default.
• W163086937 cites W2115404432 @default.
• W163086937 cites W2115826669 @default.
• W163086937 cites W2116413942 @default.
• W163086937 cites W2118745042 @default.
• W163086937 cites W2119571419 @default.
• W163086937 cites W2119679202 @default.
• W163086937 cites W2120832833 @default.
• W163086937 cites W2124231679 @default.
• W163086937 cites W2124292332 @default.
• W163086937 cites W2126776273 @default.
• W163086937 cites W2129192653 @default.
• W163086937 cites W2131953535 @default.
• W163086937 cites W2134779831 @default.
• W163086937 cites W2135730283 @default.
• W163086937 cites W2137407595 @default.
• W163086937 cites W2139891288 @default.
• W163086937 cites W2146871184 @default.
• W163086937 cites W2147071755 @default.
• W163086937 cites W2147453867 @default.
• W163086937 cites W2147982124 @default.
• W163086937 cites W2148440006 @default.
• W163086937 cites W2148603752 @default.
• W163086937 cites W2150864256 @default.
• W163086937 cites W2152717893 @default.
• W163086937 cites W2152836620 @default.
• W163086937 cites W2153628236 @default.
• W163086937 cites W2155095279 @default.
• W163086937 cites W2156194062 @default.
• W163086937 cites W2156605731 @default.
• W163086937 cites W2157579446 @default.
• W163086937 cites W2158785006 @default.

• next