4 papers
Generalizing Neural Networks by Reflecting Deviating Data in Production
Yan Xiao, Yun Lin, Ivan Beschastnikh +3
Trained with a sufficiently large training and testing dataset, Deep Neural Networks (DNNs) are expected to generalize. However, inputs may deviate from the training dataset distri…
Self-Checking Deep Neural Networks in Deployment
Yan Xiao, Ivan Beschastnikh, David S. Rosenblum +4
The widespread adoption of Deep Neural Networks (DNNs) in important domains raises questions about the trustworthiness of DNN outputs. Even a highly accurate DNN will make mistakes…
Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations
Yan Xiao, Jiafeng Guo, Yixing Fan +3
Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural repres…
Training behavior of deep neural network in frequency domain
Zhi-Qin John Xu, Yaoyu Zhang, Yanyang Xiao
Why deep neural networks (DNNs) capable of overfitting often generalize well in practice is a mystery [#zhang2016understanding]. To find a potential mechanism, we focus on the stud…