In this work, we propose an efficient and accurate full-chip thermomechanical stress and reliability analysis tool and design optimization methodology to alleviate mechanical rel...
Moongon Jung, Joydeep Mitra, David Z. Pan, Sung Ky...
Transfer learning proves to be effective for leveraging labeled data in the source domain to build an accurate classifier in the target domain. The basic assumption behind transf...
Mingsheng Long, Jianmin Wang 0001, Guiguang Ding, ...
Compared to imperative programming languages like Pascal or Basic, or functional programming languages like ML or Haskell learning Java is hampered by the fact that to get even th...
Convolution tree kernel has shown promising results in semantic role classification. However, it only carries out hard matching, which may lead to over-fitting and less accurate s...
Min Zhang, Wanxiang Che, AiTi Aw, Chew Lim Tan, Gu...
Many scalable data mining tasks rely on active learning to provide the most useful accurately labeled instances. However, what if there are multiple labeling sources (`oracles...