Heterogeneous Features Integration via Semi-supervised Multi-modal Deep Networks

2015 ◽  
pp. 11-19 ◽  
Author(s):  
Lei Zhao ◽  
Qinghua Hu ◽  
Yucan Zhou
Keyword(s):  
Heterogeneous Features ◽  
Deep Networks

Prediction of Gene Co-Expression by Quantifying Heterogeneous Features

2015 ◽  
Vol 10 (4) ◽  
pp. 414-424 ◽  
Author(s):  
Abbasali Emamjomeh ◽  
Bahram Goliaei ◽  
Javad Zahiri ◽  
Reza Ebrahimpour
Keyword(s):  
Heterogeneous Features

Study on Prediction Model of Karstic Large Spring Water Level Dynamic Coupling Multiple Factors in Jinan

2015 ◽  
Vol 8 (1) ◽  
pp. 309-317 ◽  
Author(s):  
Xing Liting ◽  
Zhou Juan ◽  
Zhang Fengjuan ◽  
Wang Song ◽  
Dou Tongwen ◽  
...  
Keyword(s):  
Prediction Model ◽  
Water Level ◽  
Spring Water ◽  
Anthropogenic Factors ◽  
Karst Water ◽  
Multiple Factors ◽  
Factors Influencing ◽  
Heterogeneous Features ◽  
Dry Seasons ◽  
Natural Decay

In karst regions, due to the heterogeneous features of karst medium, the characteristics of the groundwater flow turn to be of high complexity. Researchers have been seeking proper forecasting methods for karst water dynamic for many years. This paper, taking the spring in Jinan as an example, using regression analysis, analyzed the factors influencing spring water dynamic, and quantitatively evaluated the influencing coefficients of spring water level concerning rainfall, exploitation and recharge as well as the natural decay coefficient of spring water in dry seasons. The prediction model coupling multiple factors was built by investigating natural and anthropogenic factors influencing groundwater level, which could be used for forecasting dynamic of spring water in Jinan. The calculated value of model was highly coincided with the observed value. In consideration of the characteristics of uneven precipitation in Jinan, the suitable zones and volume of artificial recharge were investigated finally, which could help to sustain the spewing of Jinan springs significantly.

Joint Deep Networks based Multi-source Feature Learning for QoS Prediction

2021 ◽  
pp. 1-1
Author(s):  
Youhao Xia ◽  
Ding Ding ◽  
Zhenhua Chang ◽  
Fan Li
Keyword(s):  
Feature Learning ◽  
Qos Prediction ◽  
Deep Networks

Variational Methods for Machine Learning with Applications to Deep Networks

2021 ◽  
Author(s):  
Lucas Pinheiro Cinelli ◽  
Matheus Araújo Marins ◽  
Eduardo Antônio Barros da Silva ◽  
Sérgio Lima Netto
Keyword(s):  
Machine Learning ◽  
Variational Methods ◽  
Deep Networks

Polymorphic Measurement Method of FeO Content of Sinter Based on Heterogeneous Features of Infrared Thermal Images

2021 ◽  
pp. 1-1
Author(s):  
Zhaohui Jiang ◽  
Yuhao Guo ◽  
Dong Pan ◽  
Weihua Gui ◽  
Xavier Maldague
Keyword(s):  
Measurement Method ◽  
Thermal Images ◽  
Heterogeneous Features ◽  
Infrared Thermal Images

Bayesian deep networks for absolute permeability and porosity uncertainty prediction from image borehole logs from brazilian carbonate reservoirs

2021 ◽  
pp. 108361
Author(s):  
Clécio R. Bom ◽  
Manuel Blanco Valentín ◽  
Bernardo M.O. Fraga ◽  
Jorge Campos ◽  
Bernardo Coutinho ◽  
...  
Keyword(s):  
Carbonate Reservoirs ◽  
Absolute Permeability ◽  
Uncertainty Prediction ◽  
Deep Networks ◽  
Borehole Logs

A deep metric learning approach for weakly supervised loan default prediction1

2021 ◽  
pp. 1-13
Author(s):  
Kai Zhuang ◽  
Sen Wu ◽  
Xiaonan Gao
Keyword(s):  
Default Risk ◽  
Metric Learning ◽  
Real Life ◽  
Risk Scores ◽  
Loan Default ◽  
Default Prediction ◽  
Heterogeneous Features ◽  
Deep Metric Learning ◽  
Weakly Supervised ◽  
Decision Boundaries

To deal with the systematic risk of financial institutions and the rapid increasing of loan applications, it is becoming extremely important to automatically predict the default probability of a loan. However, this task is non-trivial due to the insufficient default samples, hard decision boundaries and numerous heterogeneous features. To the best of our knowledge, existing related researches fail in handling these three difficulties simultaneously. In this paper, we propose a weakly supervised loan default prediction model WEAKLOAN that systematically solves all these challenges based on deep metric learning. WEAKLOAN is composed of three key modules which are used for encoding loan features, learning evaluation metrics and calculating default risk scores. By doing so, WEAKLOAN can not only extract the features of a loan itself, but also model the hidden relationships in loan pairs. Extensive experiments on real-life datasets show that WEAKLOAN significantly outperforms all compared baselines even though the default loans for training are limited.

Sign in / Sign up

Export Citation Format

Share Document