18 citations · 52 across the 23 of their papers we have counts for
5 papers · 1 filter
Realization of spatial sparseness by deep ReLU nets with massive data
Charles K. Chui, Shao-Bo Lin, Bo Zhang +1
The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality. The depth, structure, and massive size of the data are recognize…
Fast Polynomial Kernel Classification for Massive Data
Jinshan Zeng, Minrun Wu, Shao-Bo Lin +1
In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and in…
Distributed filtered hyperinterpolation for noisy data on the sphere
Shao-Bo Lin, Yu Guang Wang, Ding-Xuan Zhou
Problems in astrophysics, space weather research and geophysics usually need to analyze noisy big data on the sphere. This paper develops distributed filtered hyperinterpolation fo…
Deep Neural Networks for Rotation-Invariance Approximation and Learning
Charles K. Chui, Shao-Bo Lin, Ding-Xuan Zhou
Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions…
Realizing data features by deep nets
Zheng-Chu Guo, Lei Shi, Shao-Bo Lin
This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some c…