Search Results for author:
Found 10 papers, 0 papers with code
Uniform Convergence of Deep Neural Networks with Lipschitz Continuous Activation Functions and Variable Widths
We consider deep neural networks with a Lipschitz continuous activation function and with weight matrices of variable widths.
Dual Information Enhanced Multi-view Attributed Graph Clustering
Specifically, the proposed method introduces the Specific Information Reconstruction (SIR) module to disentangle the explorations of the consensus and specific information from multiple views, which enables GCN to capture the more essential low-level representations.
Convergence Analysis of Deep Residual Networks
By studying the two series, we establish a sufficient condition for pointwise convergence of ResNets.
Convergence of Deep Neural Networks with General Activation Functions and Pooling
In this current work, we study the convergence of deep neural networks as the depth tends to infinity for two other important activation functions: the leaky ReLU and the sigmoid function.
Convergence of Deep Convolutional Neural Networks
Based on the conditions, we present sufficient conditions for piecewise convergence of general deep ReLU networks with increasing widths, and as well as pointwise convergence of deep ReLU convolutional neural networks.
Convergence of Deep ReLU Networks
We explore convergence of deep neural networks with the popular ReLU activation function, as the depth of the networks tends to infinity.
Exponential Approximation of Band-limited Functions from Nonuniform Sampling by Regularization Methods
Specifically, we show that one can recover a band-limited function by Gaussian or hyper-Gaussian regularized nonuniform sampling series with an exponential convergence rate.
Learning Rates for Multi-task Regularization Networks
Multi-task learning is an important trend of machine learning in facing the era of artificial intelligence and big data.
On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions
We explore a generic definition of RKBS and the reproducing kernel for RKBS that is independent of construction.
Universalities of Reproducing Kernels Revisited
The main purpose of the note is to give a delicate discussion on the universalities of weighted polynomial kernels.
