Biography: Chen Qiao is an associate professor at Xi'an Jiaotong University in China. She earned a Ph.D. in applied mathematics from Xi'an Jiaotong University in 2009. She was a visiting scholar at the University of Liverpool in UK from 2014.01-2014.04, and a Postdoc. Fellow at Tulane University in USA from 2014.11-2015.12. Her research interests include deep learning, machine learning, and Bioinformatics. She has published more than 20 papers in international refereed journals. She is the referee of 6 international journals.
Speech Title: Feature selection method by Deep learning
Abstract: Feature selection forms an important aspect of machine learning and character recognition. It is a process of selecting the most important features from raw data. In our current work, based on a novel feature back-selection method with deep belief networks, the key features/sites of several big data sets are obtained, and they are used for saving the storage space as well as getting satisfied classification accuracy. Both the space saving rates and the classification accuracy rates show the efficient of this approach. The method presented here provides a new way to gain traction on further understanding high-dimensional data by deep learning, especially lies in promoting new applications of deep learning on the field of feature selection.