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.
|Number of pages||9|
|Journal||International Journal of Networked and Distributed Computing|
|Publication status||Published - 2018 Dec|
Bibliographical noteFunding Information:
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (Grant number: NRF-2018R1D1A1A09081956).
© 2018 The Authors. Published by Atlantis Press SARL.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Computer Networks and Communications