Kernel and Range Approach to Analytic Network Learning

DOI

10.2991/ijndc.2018.7.1.3How to use a DOI?

Keywords

Least squares error; linear algebra; multilayer neural networks

Abstract

A novel learning approach for a composite function that can be written in the form of a matrix system of linear equations is introduced in this paper. This learning approach, which is gradient-free, is grounded upon the observation that solving the system of linear equations by manipulating the kernel and the range projection spaces using the Moore–Penrose inversion boils down to an approximation in the least squares error sense. In view of the heavy dependence on computation of the pseudoinverse, a simplification method is proposed. The learning approach is applied to learn a multilayer feedforward neural network with full weight connections. The numerical experiments on learning both synthetic and benchmark data sets not only validate the feasibility but also depict the performance of the proposed formulation.

Copyright

© 2018 The Authors. Published by Atlantis Press SARL.

Open Access

This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Kar-Ann Toh
PY  - 2018
DA  - 2018/12/31
TI  - Kernel and Range Approach to Analytic Network Learning
JO  - International Journal of Networked and Distributed Computing
SP  - 20
EP  - 28
VL  - 7
IS  - 1
SN  - 2211-7946
UR  - https://doi.org/10.2991/ijndc.2018.7.1.3
DO  - 10.2991/ijndc.2018.7.1.3
ID  - Toh2018
ER  -