A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a `show-and-tell' procedu...
We propose a multiple source domain adaptation method, referred to as Domain Adaptation Machine (DAM), to learn a robust decision function (referred to as target classifier) for l...
Many kernel learning methods have to assume parametric forms for the target kernel functions, which significantly limits the capability of kernels in fitting diverse patterns. Som...
Code obfuscation makes it harder for a security analyst to understand the malicious payload of a program. In most cases an analyst needs to study the program at the machine code l...
Most current multi-task learning frameworks ignore the robustness issue, which means that the presence of "outlier" tasks may greatly reduce overall system performance. ...