李进教授：

The fusion of machine learning, image processing and security as an emerging paradigm to protect the privacy of clients and classifier.

李松教授：

Constrained least absolute deviation (LAD) problems often arise from sparse regression of statistical prediction and compressed sensing literature. It is challenging to solve LAD problems with sparsity constraints directly due to non-smoothness of objective functions and non-convex feasible sets. We provide an adaptive iterative hard thresholding (AIHT) method to solve LAD problems with sparsity constraints. 

文再文教授：

深度学习中高度非凸非线性优化问题由于维数灾难求解十分困难，发展准确、 快速、实时的随机优化算法非常重要。

冼军教授：

The stratified samples could produce more uniform point distribution configuration than crude Monte Carlo sampling point set. 

史治国教授：

随着宽带信号在雷达/传感系统中的大规模应用，传统的奈奎斯特接收机越来越依赖于高性能的模数转换组件，给系统带来了高昂的成本。压缩感知理论很好地解决了雷达/传感系统参数估计性能与系统软硬件成本之间的权衡问题，因此基于压缩感知的参数估计在过去十年中引起了广泛的研究兴趣。

许志强研究员：

Zhang-Suen parallel thinning algorithm with the feature of rapidity and practicality ensures the connectivity of the refined curve. However, the refined skeleton cannot be guaranteed in a single pixel wide, and redundancy segments are generated due to acute angles.