8 citations · 18 across the 9 of their papers we have counts for
11 papers
Difference of Convex (DC) approach for neural network approximation with uniform loss function
Vinesha Peiris, Nadezda Sukhorukova
Neural networks (NNs) can be viewed as approximation tools. Traditionally, NNs are relying on gradient and stochastic gradient (SG) methods. There are a number of available computa…
KKT-based optimality conditions for neural network approximation
Vinesha Peiris, Nadezda Sukhorukova, Julien Ugon
In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ( norm) and Chebyshev ( norm). The op…
Nonsmooth Optimisation and neural networks
Vinesha Peiris, Nadezda Sukhorukova
In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approxima…
Best free knot linear spline approximation and its application to neural networks
Vinesha Peiris, Duy Khoa Pham, Nadezda Sukhorukova
The problem of fixed knot approximation is convex and there are several efficient approaches to solve this problem, yet, when the knots joining the affine parts are also variable,…
A comparison of rational and neural network based approximations
Vinesha Peiris, Reinier Diaz Millan, Nadezda Sukhorukova +1
Rational and neural network based approximations are efficient tools in modern approximation. These approaches are able to produce accurate approximations to nonsmooth and non-Lips…
Rational activation functions in neural networks with uniform based loss functions and its application in classification
Vinesha Peiris
In this paper, we demonstrate the application of generalised rational uniform (Chebyshev) approximation in neural networks. In particular, our activation functions are one degree r…
Flexible rational approximation and its application for matrix functions
Nir Sharon, Vinesha Peiris, Nadia Sukhorukova +1
This paper proposes a unique optimization approach for estimating the minimax rational approximation and its application for evaluating matrix functions. Our method enables the ext…
Deep Learning with Nonsmooth Objectives
Vinesha Peiris, Nadezda Sukhorukova, Vera Roshchina
We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior cl…
Multivariate approximation by polynomial and generalised rational functions
R. Díaz Millán, V. Peiris, N. Sukhorukova +1
In this paper we develop an optimisation based approach to multivariate Chebyshev approximation on a finite grid. We consider two models: multivariate polynomial approximation and…
The extension of linear inequality method for generalised rational Chebyshev approximation to approximation by general quasilinear functions
Vinesha Peiris, Nadezda Sukhorukova
In this paper we demonstrate that a well known linear inequality method developed for rational Chebyshev approximation is equivalent to the application of the bisection method used…
Rational approximation and its application to improving deep learning classifiers
V. Peiris, N. Sharon, N. Sukhorukova J. Ugon
A rational approximation by a ratio of polynomial functions is a flexible alternative to polynomial approximation. In particular, rational functions exhibit accurate estimations to…