39 citations · 55 across the 6 of their papers we have counts for
6 papers
PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units
Bo Li, Shanshan Tang, Haijun Yu
Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not con…
Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units
Bo Li, Shanshan Tang, Haijun Yu
Deep neural networks with rectified linear units (ReLU) are getting more and more popular due to their universal representation power and successful applications. Some theoretical…
Application of Bounded Total Variation Denoising in Urban Traffic Analysis
Shanshan Tang, Haijun Yu
While it is believed that denoising is not always necessary in many big data applications, we show in this paper that denoising is helpful in urban traffic analysis by applying the…
Subharmonic solutions of first order Hamiltonian systems with subquadratic condition
Shanshan Tang
Using a homologically link theorem in variational theory and iteration inequalities of Maslov-type index, we prove the existences of a sequence of subharmonic solutions for one typ…
Dual morse index estimates and application to Hamiltonian systems with P-boundary conditions
Shanshan Tang
In this paper, we study the multiplicity of Hamiltonian systems with P-boundary conditions.
Minimal -symmetric periodic solutions of nonlinear Hamiltonian systems
Shanshan Tang
In this paper some existence results for the minimal P-symmetric periodic solutions are proved for first order autonomous Hamiltonian systems when the Hamiltonian function is super…