Adversarial Ladder Networks
| Title: | Adversarial Ladder Networks |
|---|---|
| Authors: | Molano, Juan Maroñas, Colomer, Alberto Albiol, Palacios, Roberto Paredes |
| Publication Year: | 2016 |
| Collection: | Computer Science Statistics |
| Subject Terms: | Computer Science - Neural and Evolutionary Computing, Computer Science - Learning, Statistics - Machine Learning |
| More Details: | The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializing the weights of the network and after these weights are refined with the use of supervised data. On the other hand adversarial noise has improved the results of clas- sical supervised learning. Recently, a new neural network topology called Ladder Network, where the key idea is based in some properties of hierar- chichal latent variable models, has been proposed as a technique to train a neural network using supervised and unsupervised data at the same time with what is called semi-supervised learning. This technique has reached state of the art classification. In this work we add adversarial noise to the ladder network and get state of the art classification, with several important conclusions on how adversarial noise can help in addition with new possible lines of investi- gation. We also propose an alternative to add adversarial noise to unsu- pervised data. |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/1611.02320 |
| Accession Number: | edsarx.1611.02320 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/1611.02320 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20161107&spage=&pages=&title=Adversarial Ladder Networks&atitle=Adversarial%20Ladder%20Networks&aulast=Molano%2C%20Juan%20Maro%C3%B1as&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.1611.02320 RelevancyScore: 960 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 959.910522460938 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Adversarial Ladder Networks – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Molano%2C+Juan+Maroñas%22">Molano, Juan Maroñas</searchLink><br /><searchLink fieldCode="AR" term="%22Colomer%2C+Alberto+Albiol%22">Colomer, Alberto Albiol</searchLink><br /><searchLink fieldCode="AR" term="%22Palacios%2C+Roberto+Paredes%22">Palacios, Roberto Paredes</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2016 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science<br />Statistics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Neural+and+Evolutionary+Computing%22">Computer Science - Neural and Evolutionary Computing</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Learning%22">Computer Science - Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Statistics+-+Machine+Learning%22">Statistics - Machine Learning</searchLink> – Name: Abstract Label: Description Group: Ab Data: The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializing the weights of the network and after these weights are refined with the use of supervised data. On the other hand adversarial noise has improved the results of clas- sical supervised learning. Recently, a new neural network topology called Ladder Network, where the key idea is based in some properties of hierar- chichal latent variable models, has been proposed as a technique to train a neural network using supervised and unsupervised data at the same time with what is called semi-supervised learning. This technique has reached state of the art classification. In this work we add adversarial noise to the ladder network and get state of the art classification, with several important conclusions on how adversarial noise can help in addition with new possible lines of investi- gation. We also propose an alternative to add adversarial noise to unsu- pervised data. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/1611.02320" linkWindow="_blank">http://arxiv.org/abs/1611.02320</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.1611.02320 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.1611.02320 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Neural and Evolutionary Computing Type: general – SubjectFull: Computer Science - Learning Type: general – SubjectFull: Statistics - Machine Learning Type: general Titles: – TitleFull: Adversarial Ladder Networks Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Molano, Juan Maroñas – PersonEntity: Name: NameFull: Colomer, Alberto Albiol – PersonEntity: Name: NameFull: Palacios, Roberto Paredes IsPartOfRelationships: – BibEntity: Dates: – D: 07 M: 11 Type: published Y: 2016 |
| ResultId | 1 |