We propose a new bound for generalization of neural networks using Koopm...
Ridgelet transform has been a fundamental mathematical tool in the
theor...
We investigate the approximation property of group convolutional neural
...
Neural network on Riemannian symmetric space such as hyperbolic space an...
A biological neural network in the cortex forms a neural field. Neurons ...
Random features are a central technique for scalable learning algorithms...
Overparametrization has been remarkably successful for deep learning stu...
We detail a novel class of implicit neural models. Leveraging time-paral...
A random net is a shallow neural network where the hidden layer is froze...
Deep learning achieves a high generalization performance in practice, de...
Kernel methods augmented with random features give scalable algorithms f...
We propose a new numerical integration method for training a shallow neu...
We have obtained an integral representation of the shallow neural networ...
The feature map obtained from the denoising autoencoder (DAE) is investi...
Data representation in a stacked denoising autoencoder is investigated.
...
This paper presents an investigation of the approximation property of ne...
A new initialization method for hidden parameters in a neural network is...