2 papers
cs.NE2016
Multi-pretrained Deep Neural Network
Zhen Hu, Zhuyin Xue, Tong Cui +2
Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pr…
cs.LG2016
On the Complexity of One-class SVM for Multiple Instance Learning
Zhen Hu, Zhuyin Xue
In traditional multiple instance learning (MIL), both positive and negative bags are required to learn a prediction function. However, a high human cost is needed to know the label…