Source-Target-Source Classification Using Stacked Denoising Autoencoders
Source-Target-Source Classification Using Stacked Denoising Autoencoders
dc.contributor.author | Kandaswamy,C | en |
dc.contributor.author | Silva,LM | en |
dc.contributor.author | Jaime Cardoso | en |
dc.date.accessioned | 2018-01-21T16:00:13Z | |
dc.date.available | 2018-01-21T16:00:13Z | |
dc.date.issued | 2015 | en |
dc.description.abstract | 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. | en |
dc.identifier.uri | http://repositorio.inesctec.pt/handle/123456789/7189 | |
dc.identifier.uri | http://dx.doi.org/10.1007/978-3-319-19390-8_5 | en |
dc.language | eng | en |
dc.relation | 3889 | en |
dc.rights | info:eu-repo/semantics/openAccess | en |
dc.title | Source-Target-Source Classification Using Stacked Denoising Autoencoders | en |
dc.type | conferenceObject | en |
dc.type | Publication | en |
Files
Original bundle
1 - 1 of 1