COFFIN: A Computational Framework for Linear SVMs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00166480" target="_blank" >RIV/68407700:21230/09:00166480 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

COFFIN: A Computational Framework for Linear SVMs

Popis výsledku v původním jazyce

In a variety of applications, kernel machines such as Support Vector Machines (SVMs) have been used with great success often delivering state-of-the-art results. Using the kernel trick, they work on several domains and even enable heterogeneous data fusion by concatenating feature spaces or multiple kernel learning. Unfortunately, they are not suited for truly large-scale applications since they suffer from the curse of supporting vectors, e.g., the speed of applying SVMs decays linearly with the numberof support vectors. In this paper we develop COFFIN - a new training strategy for linear SVMs that effectively allows the use of on demand computed kernel feature spaces and virtual examples in the primal. With linear training and prediction effort thisframework leverages SVM applications to truly large-scale problems: As an example, we train SVMs for human splice site recognition involving 50 million examples and sophisticated string kernels.

Název v anglickém jazyce

COFFIN: A Computational Framework for Linear SVMs

Popis výsledku anglicky

In a variety of applications, kernel machines such as Support Vector Machines (SVMs) have been used with great success often delivering state-of-the-art results. Using the kernel trick, they work on several domains and even enable heterogeneous data fusion by concatenating feature spaces or multiple kernel learning. Unfortunately, they are not suited for truly large-scale applications since they suffer from the curse of supporting vectors, e.g., the speed of applying SVMs decays linearly with the numberof support vectors. In this paper we develop COFFIN - a new training strategy for linear SVMs that effectively allows the use of on demand computed kernel feature spaces and virtual examples in the primal. With linear training and prediction effort thisframework leverages SVM applications to truly large-scale problems: As an example, we train SVMs for human splice site recognition involving 50 million examples and sophisticated string kernels.

Druh

O - Ostatní výsledky

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2009

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů