4 papers
Neural Network Approximation: Three Hidden Layers Are Enough
Zuowei Shen, Haizhao Yang, Shijun Zhang
A three-hidden-layer neural network with super approximation power is introduced. This network is built with the floor function (), the exponential function ($2^x…
Deep Network with Approximation Error Being Reciprocal of Width to Power of Square Root of Depth
Zuowei Shen, Haizhao Yang, Shijun Zhang
A new network with super approximation power is introduced. This network is built with Floor () or ReLU () activation function in each neuron and hen…
Deep Network Approximation Characterized by Number of Neurons
Zuowei Shen, Haizhao Yang, Shijun Zhang
This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons. It is shown by construction that ReLU…
Nonlinear Approximation via Compositions
Zuowei Shen, Haizhao Yang, Shijun Zhang
Given a function dictionary and an approximation budget , nonlinear approximation seeks the linear combination of the best terms $\{T_n\}_{1\le n\le…