The training of two-layer neural networks with nonlinear activation functions is an important
non-convex optimization problem with numerous applications and promising performance in …

Polynomials, which are widely used to study non-linear systems, have been shown to be
extremely useful in analyzing neural networks (NNs). However, the existing methods for …

The training of two-layer neural networks with nonlinear activation functions is an important
non-convex optimization problem with numerous applications and promising performance in …

Electromagnetic actuator systems composed of an induction servo motor (ISM) drive system
and a rice milling machine system have widely been used in agricultural applications. In …

We consider the problem of finding a two-layer neural network with sigmoid, rectified linear
unit (ReLU), or binary step activation functions that “fits” a training data set as accurately as …

We focus on several algorithmic problems arising from the study of random combinatorial
structures and of neural network models, with a particular emphasis on computational …

In this paper, we propose a hybrid ensemble polynomial neural network (HEPNN) with the
aid of polynomial neural network (PNN) and hybrid ensemble polynomials neurons …

Polynomial functions have plenty of useful analytical properties, but they are rarely used as
learning models because their function class is considered to be restricted. This work shows …

A combination of neural networks and polynomial functions offers some favorable theoretical
properties to neural network. Polynomial neural networks limit the model functions to …