Classification with neural networks with quadratic decision functions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Frischauf, Leon, Scherzer, Otmar, Shi, Cong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909230873706496
author Frischauf, Leon
Scherzer, Otmar
Shi, Cong
author_facet Frischauf, Leon
Scherzer, Otmar
Shi, Cong
contents Neural networks with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear ones. They are advantageous when the objects or classes to be identified are compact and of basic geometries like circles, ellipses etc. In this paper we investigate the use of such ansatz functions for classification. In particular we test and compare the algorithm on the MNIST dataset for classification of handwritten digits and for classification of subspecies. We also show, that the implementation can be based on the neural network structure in the software Tensorflow and Keras, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classification with neural networks with quadratic decision functions
Frischauf, Leon
Scherzer, Otmar
Shi, Cong
Machine Learning
Numerical Analysis
49N45, 41A30, 65XX, 68TXX
Neural networks with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear ones. They are advantageous when the objects or classes to be identified are compact and of basic geometries like circles, ellipses etc. In this paper we investigate the use of such ansatz functions for classification. In particular we test and compare the algorithm on the MNIST dataset for classification of handwritten digits and for classification of subspecies. We also show, that the implementation can be based on the neural network structure in the software Tensorflow and Keras, respectively.
title Classification with neural networks with quadratic decision functions
topic Machine Learning
Numerical Analysis
49N45, 41A30, 65XX, 68TXX
url https://arxiv.org/abs/2401.10710