Autoencoders Covering Space as a Life-Long Classifier

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332666" target="_blank" >RIV/68407700:21230/19:00332666 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-19642-4_27" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-19642-4_27</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-19642-4_27" target="_blank" >10.1007/978-3-030-19642-4_27</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Autoencoders Covering Space as a Life-Long Classifier

Popis výsledku v původním jazyce

A life-long classifier that learns incrementally has many challenges such as concept drift, when the class changes in time, and catastrophic forgetting when the earlier learned knowledge is lost. Many successful connectionist solutions are based on an idea that new data are learned only in a part of a network that is relevant to the new data. We leverage this idea and propose a novel method for learning an ensemble of specialized autoencoders. We interpret autoencoders as manifolds that can be trained to contain or exclude given points from the input space. This manifold manipulation allows us to implement a classifier that can suppress catastrophic forgetting and adapt to concept drift. The proposed algorithm is evaluated on an incremental version of the XOR problem and on an incremental version of the MNIST classification where we achieved 0.9 accuracy which is a significant improvement over the previously published results

Název v anglickém jazyce

Autoencoders Covering Space as a Life-Long Classifier

Popis výsledku anglicky

A life-long classifier that learns incrementally has many challenges such as concept drift, when the class changes in time, and catastrophic forgetting when the earlier learned knowledge is lost. Many successful connectionist solutions are based on an idea that new data are learned only in a part of a network that is relevant to the new data. We leverage this idea and propose a novel method for learning an ensemble of specialized autoencoders. We interpret autoencoders as manifolds that can be trained to contain or exclude given points from the input space. This manifold manipulation allows us to implement a classifier that can suppress catastrophic forgetting and adapt to concept drift. The proposed algorithm is evaluated on an incremental version of the XOR problem and on an incremental version of the MNIST classification where we achieved 0.9 accuracy which is a significant improvement over the previously published results

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

<a href="/cs/project/GA18-18858S" target="_blank" >GA18-18858S: Metody kontinuálního učení řízení pohybu vícenohých kráčejích robotů v úlohách autonomního sběru dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization

ISBN

978-3-030-19641-7

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

11

Strana od-do

271-281

Název nakladatele

Springer-VDI-Verlag

Místo vydání

Düsseldorf

Místo konání akce

Barcelona

Datum konání akce

26. 6. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—