Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning
| Autor: | Kei Ujimoto, Yoshikuni Sato, Toru Nakada, Nobuhiro Hayashi, Yoshihide Sawada, Shunta Yamaguchi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Relation (database)
Computer science transfer learning lcsh:Technology sepsis classification Domain (software engineering) lcsh:Chemistry proteomics General Materials Science Point (geometry) Divergence (statistics) Instrumentation lcsh:QH301-705.5 Fluid Flow and Transfer Processes business.industry lcsh:T Process Chemistry and Technology Deep learning General Engineering deep neural network lcsh:QC1-999 Computer Science Applications Constraint (information theory) lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 Pairwise comparison Artificial intelligence business Transfer of learning lcsh:Engineering (General). Civil engineering (General) Algorithm lcsh:Physics |
| Zdroj: | Applied Sciences Volume 9 Issue 1 Applied Sciences, Vol 9, Iss 1, p 128 (2019) |
| Popis: | This paper proposes a target vector modification method for the all-transfer deep learning (ATDL) method. Deep neural networks (DNNs) have been used widely in many applications however, the DNN has been known to be problematic when large amounts of training data are not available. Transfer learning can provide a solution to this problem. Previous methods regularize all layers, including the output layer, by estimating the relation vectors, which are then used instead of one-hot target vectors of the target domain. These vectors are estimated by averaging the target domain data of each target domain label in the output space. This method improves the classification performance, but it does not consider the relation between the relation vectors. From this point of view, we propose a relation vector modification based on constrained pairwise repulsive forces. High pairwise repulsive forces provide large distances between the relation vectors. In addition, the risk of divergence is mitigated by the constraint based on distributions of the output vectors of the target domain data. We apply our method to two simulation experiments and a disease classification using two-dimensional electrophoresis images. The experimental results show that reusing all layers through our estimation method is effective, especially for a significantly small number of the target domain data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|