Multi-target deep neural networks: Theoretical analysis and implementation

• المؤلفون الرئيسيون: ZENG, Zeng, LIANG, Nanying, YANG, Xulei, HOI, Steven C. H.
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2018
• الموضوعات: Object detection; Segmentation; Learning path; Multi-target deep learning; Deep neural networks; Databases and Information Systems; OS and Networks
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/4200; https://ink.library.smu.edu.sg/context/sis_research/article/5203/viewcontent/Multi_target_deep_neural_networks_afv.pdf

In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model...