most citedOverfitting Mechanism and Avoidance in Deep Neural Networks

108 citations · 108 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL2020

An Analysis on the Learning Rules of the Skip-Gram Model

Canlin Zhang, Xiuwen Liu, Daniel Bis

To improve the generalization of the representations for natural language processing tasks, words are commonly represented using vectors, where distances among the vectors are rela…

cs.LG2019

Towards Quantifying Intrinsic Generalization of Deep ReLU Networks

Shaeke Salman, Canlin Zhang, Xiuwen Liu +1

Understanding the underlying mechanisms that enable the empirical successes of deep neural networks is essential for further improving their performance and explaining such network…

cs.SI2019

Next-Generation High-Resolution Vector-Borne Disease Risk Assessment

Meysam Ghaffari, Ashok Srinivasan, Anuj Mubayi +2

Vector-borne diseases cause more than 1 million deaths annually. Estimates of epidemic risk at high spatial resolutions can enable effective public health interventions. Our goal i…

cs.LG2019

Consensus-based Interpretable Deep Neural Networks with Application to Mortality Prediction

Shaeke Salman, Seyedeh Neelufar Payrovnaziri, Xiuwen Liu +2

Deep neural networks have achieved remarkable success in various challenging tasks. However, the black-box nature of such networks is not acceptable to critical applications, such…

cs.SI2019

High-resolution home location prediction from tweets using deep learning with dynamic structure

Meysam Ghaffari, Ashok Srinivasan, Xiuwen Liu

Timely and high-resolution estimates of the home locations of a sufficiently large subset of the population are critical for effective disaster response and public health intervent…

cs.LG2019108 cited

Overfitting Mechanism and Avoidance in Deep Neural Networks

Shaeke Salman, Xiuwen Liu

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult t…