Using Neural Network Formalism to Solve Multiple-Instance Problems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315379" target="_blank" >RIV/68407700:21230/17:00315379 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-319-59072-1_17" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-319-59072-1_17</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-59072-1_17" target="_blank" >10.1007/978-3-319-59072-1_17</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using Neural Network Formalism to Solve Multiple-Instance Problems

Popis výsledku v původním jazyce

a fixed length, whereas describing them by means of a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining in importance throughout the last years. MIL formalism assumes that each object (sample) is represented by a set (bag) of feature vectors (instances) of fixed length, where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in the late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to 14 types of classifiers from the prior art on a set of 20 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.

Název v anglickém jazyce

Using Neural Network Formalism to Solve Multiple-Instance Problems

Popis výsledku anglicky

a fixed length, whereas describing them by means of a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining in importance throughout the last years. MIL formalism assumes that each object (sample) is represented by a set (bag) of feature vectors (instances) of fixed length, where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in the late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to 14 types of classifiers from the prior art on a set of 20 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Advances in Neural Networks - ISNN 2017

ISBN

978-3-319-59071-4

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

8

Strana od-do

135-142

Název nakladatele

Springer

Místo vydání

Wien

Místo konání akce

Hokkaido

Datum konání akce

21. 6. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—