FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2210514981> ?p ?o ?g. }

• W2210514981 abstract "This thesis studies the problem of supervised learning using a family of machines, namely kernel learning machines. A number of standard learning methods belong to this family, such as Regularization Networks (RN) and Support Vector Machines (SVM). The thesis presents a theoretical justification of these machines within a unified framework based on the statistical learning theory of Vapnik. The generalization performance of RN and SVM is studied within this framework, and bounds on the generalization error of these machines are proved. In the second part, the thesis goes beyond standard one-layer learning machines, and probes into the problem of learning using hierarchical learning schemes. In particular it investigates the question: what happens when instead of training one machine using the available examples we train many of them, each in a different way, and then combine the machines? Two types of ensembles are defined: voting combinations and adaptive combinations. The statistical properties of these hierarchical learning schemes are investigated both theoretically and experimentally: bounds on their generalization performance are proved, and experiments characterizing their behavior are shown. Finally, the last part of the thesis discusses the problem of choosing data representations for learning. It is an experimental part that uses the particular problem of object detection in images as a framework to discuss a number of issues that arise when kernel machines are used in practice. Thesis Supervisor: Tomaso Poggio Title: Uncas and Helen Whitaker Professor of Brain and Cognitive Sciences" @default.
• W2210514981 created "2016-06-24" @default.
• W2210514981 creator A5022937525 @default.
• W2210514981 date "2000-01-01" @default.
• W2210514981 modified "2023-09-24" @default.
• W2210514981 title "Learning with kernel machine architectures" @default.
• W2210514981 cites W1512098439 @default.
• W2210514981 cites W1530699444 @default.
• W2210514981 cites W1548393923 @default.
• W2210514981 cites W1548502347 @default.
• W2210514981 cites W1564947197 @default.
• W2210514981 cites W1634005169 @default.
• W2210514981 cites W1680579736 @default.
• W2210514981 cites W1761010383 @default.
• W2210514981 cites W1848067327 @default.
• W2210514981 cites W1924225422 @default.
• W2210514981 cites W1965720095 @default.
• W2210514981 cites W1965999112 @default.
• W2210514981 cites W1975846642 @default.
• W2210514981 cites W1981025032 @default.
• W2210514981 cites W1986280275 @default.
• W2210514981 cites W1989408439 @default.
• W2210514981 cites W1995558350 @default.
• W2210514981 cites W2005201432 @default.
• W2210514981 cites W2010029425 @default.
• W2210514981 cites W2012530041 @default.
• W2210514981 cites W2017753243 @default.
• W2210514981 cites W2019635781 @default.
• W2210514981 cites W2024046085 @default.
• W2210514981 cites W2024897640 @default.
• W2210514981 cites W2029538739 @default.
• W2210514981 cites W2030561575 @default.
• W2210514981 cites W2034374737 @default.
• W2210514981 cites W2046130948 @default.
• W2210514981 cites W2049600989 @default.
• W2210514981 cites W2050297026 @default.
• W2210514981 cites W2055940788 @default.
• W2210514981 cites W2056695679 @default.
• W2210514981 cites W2056735347 @default.
• W2210514981 cites W2056763477 @default.
• W2210514981 cites W2059811159 @default.
• W2210514981 cites W2069888879 @default.
• W2210514981 cites W2077390566 @default.
• W2210514981 cites W2077424406 @default.
• W2210514981 cites W2079088811 @default.
• W2210514981 cites W2090102379 @default.
• W2210514981 cites W2090344516 @default.
• W2210514981 cites W2097629057 @default.
• W2210514981 cites W2098693229 @default.
• W2210514981 cites W2098774896 @default.
• W2210514981 cites W2099579348 @default.
• W2210514981 cites W2100115174 @default.
• W2210514981 cites W2104671481 @default.
• W2210514981 cites W2106491486 @default.
• W2210514981 cites W2108429620 @default.
• W2210514981 cites W2115763357 @default.
• W2210514981 cites W2119821739 @default.
• W2210514981 cites W2123507038 @default.
• W2210514981 cites W2125713050 @default.
• W2210514981 cites W2129192653 @default.
• W2210514981 cites W2137346077 @default.
• W2210514981 cites W2138263042 @default.
• W2210514981 cites W2138745909 @default.
• W2210514981 cites W2139212933 @default.
• W2210514981 cites W2141038809 @default.
• W2210514981 cites W2143956139 @default.
• W2210514981 cites W2147800946 @default.
• W2210514981 cites W2148603752 @default.
• W2210514981 cites W2149208907 @default.
• W2210514981 cites W2149846618 @default.
• W2210514981 cites W2150434953 @default.
• W2210514981 cites W2153755271 @default.
• W2210514981 cites W2154597830 @default.
• W2210514981 cites W2156512439 @default.
• W2210514981 cites W2156909104 @default.
• W2210514981 cites W2158078575 @default.
• W2210514981 cites W2159173611 @default.
• W2210514981 cites W2159686933 @default.
• W2210514981 cites W2161813919 @default.
• W2210514981 cites W2166473218 @default.
• W2210514981 cites W2408196097 @default.
• W2210514981 cites W2567032824 @default.
• W2210514981 cites W2571441540 @default.
• W2210514981 cites W2797583072 @default.
• W2210514981 cites W2914369697 @default.
• W2210514981 cites W3017143921 @default.
• W2210514981 cites W3022664448 @default.
• W2210514981 cites W3169507310 @default.
• W2210514981 cites W2531834939 @default.
• W2210514981 hasPublicationYear "2000" @default.
• W2210514981 type Work @default.
• W2210514981 sameAs 2210514981 @default.
• W2210514981 citedByCount "4" @default.
• W2210514981 crossrefType "dissertation" @default.
• W2210514981 hasAuthorship W2210514981A5022937525 @default.
• W2210514981 hasConcept C115903097 @default.
• W2210514981 hasConcept C119857082 @default.
• W2210514981 hasConcept C122280245 @default.
• W2210514981 hasConcept C12267149 @default.
• W2210514981 hasConcept C134306372 @default.

• next