Pages that link to "Item:Q663685"

The following pages link to Approximation by neural networks with weights varying on a finite set of directions (Q663685):

Displaying 14 items.

• On the approximation by neural networks with bounded number of neurons in hidden layers (Q483038) (← links)
• The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks (Q521720) (← links)
• On the representation by bivariate ridge functions (Q2058579) (← links)
• Rates of approximation by neural network interpolation operators (Q2073064) (← links)
• On the approximation by single hidden layer feedforward neural networks with fixed weights (Q2179313) (← links)
• Almost everywhere approximation capabilities of double Mellin approximate identity neural networks (Q2403275) (← links)
• Approximation by ridge functions and neural networks with a bounded number of neurons (Q3452446) (← links)
• (Q5080573) (← links)
• Neural network interpolation operators activated by smooth ramp functions (Q5083442) (← links)
• Approximation Properties of Ridge Functions and Extreme Learning Machines (Q5154637) (← links)
• Approximation by sums of ridge functions with fixed directions (Q5369335) (← links)
• Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions (Q5378401) (← links)
• A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function (Q5380543) (← links)
• Approximation error of single hidden layer neural networks with fixed weights (Q6195340) (← links)