Source-Target-Source Classification Using Stacked Denoising Autoencoders

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2015

Autores

Chetak Kandaswamy (Autor) Outra; Luis M Silva (Autor) Outra; Jaime S Cardoso (Autor) FEUP

Ata de Conferência Internacional

Título: PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015)

Páginas: 39-47

7th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)

Santiago de Compostela, SPAIN, JUN 17-19, 2015

Indexação

ISI Web of Knowledge - 2 Citações

Scopus - 2 Citações

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

Outras Informações

ID Authenticus: P-00G-EAK

DOI: 10.1007/978-3-319-19390-8_5

Abstract (EN): Deep Transfer Learning (DTL) emerged as a new paradigm in machine learning in which a deep model is trained on a source task and the knowledge acquired is then totally or partially transferred to help in solving a target task. Even though DTL offers a greater flexibility in extracting high-level features and enabling feature transference from a source to a target task, the DTL solution might get stuck at local minima leading to performance degradation-negative transference-, similar to what happens in the classical machine learning approach. In this paper, we propose the Source-Target-Source (STS) methodology to reduce the impact of negative transference, by iteratively switching between source and target tasks in the training process. The results show the effectiveness of such approach.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 9