Cargando…
Structured (De)composable Representations Trained with Neural Networks
The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composab...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7459355/ http://dx.doi.org/10.1007/978-3-030-58309-5_3 |
_version_ | 1783576357700108288 |
---|---|
author | Spinks, Graham Moens, Marie-Francine |
author_facet | Spinks, Graham Moens, Marie-Francine |
author_sort | Spinks, Graham |
collection | PubMed |
description | The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing to decompose the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data). |
format | Online Article Text |
id | pubmed-7459355 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
record_format | MEDLINE/PubMed |
spelling | pubmed-74593552020-09-01 Structured (De)composable Representations Trained with Neural Networks Spinks, Graham Moens, Marie-Francine Artificial Neural Networks in Pattern Recognition Article The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing to decompose the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data). 2020-08-05 /pmc/articles/PMC7459355/ http://dx.doi.org/10.1007/978-3-030-58309-5_3 Text en © The Author(s) 2020 Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence and indicate if changes were made. The images or other third party material in this chapter are included in the chapter's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. |
spellingShingle | Article Spinks, Graham Moens, Marie-Francine Structured (De)composable Representations Trained with Neural Networks |
title | Structured (De)composable Representations Trained with Neural Networks |
title_full | Structured (De)composable Representations Trained with Neural Networks |
title_fullStr | Structured (De)composable Representations Trained with Neural Networks |
title_full_unstemmed | Structured (De)composable Representations Trained with Neural Networks |
title_short | Structured (De)composable Representations Trained with Neural Networks |
title_sort | structured (de)composable representations trained with neural networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7459355/ http://dx.doi.org/10.1007/978-3-030-58309-5_3 |
work_keys_str_mv | AT spinksgraham structureddecomposablerepresentationstrainedwithneuralnetworks AT moensmariefrancine structureddecomposablerepresentationstrainedwithneuralnetworks |