Deep supervised learning with mixture of neural networks.
Deep Neural Network (DNN), as a deep architectures, has shown excellent performance in classification tasks. However, when the data has different distributions or contains some latent non-observed factors, it is difficult for DNN to train a single model to perform well on the classification tasks. I...
| Publicado en: | Artificial Intelligence in Medicine Vol. 102 |
|---|---|
| Autores principales: | , , , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Elsevier B.V.
Jan2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=141319867&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 141319867 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09333657 3HY jtl: Artificial Intelligence in Medicine issn: 09333657 maglogo: N pubinfo: dt: Jan2020 vid: 102 pid: 1004 pub: Elsevier B.V. artinfo: ui: 141319867 141319867 NLM31980101 141319867 10.1016/j.artmed.2019.101764 NLM31980101 141319867 ppct: 1 formats: tig: atl: Deep supervised learning with mixture of neural networks. aug: au: Hu, Yaxian Luo, Senlin Han, Longfei Pan, Limin Zhang, Tiemei affil: Information System & Security and Countermeasures Experiments Center, Beijing Institute of Technology, 100081, PR China sug: subj: Computer Simulation Handwriting Female Breast Neoplasms Diagnosis Information Science Human Algorithms Classification Resource Databases Diabetes Mellitus Diagnosis Validation Studies Comparative Studies Evaluation Research Multicenter Studies Female ab: Deep Neural Network (DNN), as a deep architectures, has shown excellent performance in classification tasks. However, when the data has different distributions or contains some latent non-observed factors, it is difficult for DNN to train a single model to perform well on the classification tasks. In this paper, we propose mixture model based on DNNs (MoNNs), a supervised approach to perform classification tasks with a gating network and multiple local expert models. We use a neural network as a gating function and use DNNs as local expert models. The gating network split the heterogeneous data into several homogeneous components. DNNs are combined to perform classification tasks in each component. Moreover, we use EM (Expectation Maximization) as an optimization algorithm. Experiments proved that our MoNNs outperformed the other compared methods on determination of diabetes, determination of benign or malignant breast cancer, and handwriting recognition. Therefore, the MoNNs can solve the problem of data heterogeneity and have a good effect on classification tasks. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|