Towards a constructive multilayer perceptron for regression task using non-parametric clustering. A case study of Photo-Z redshift reconstruction
This addresses the challenge of architecture selection for neural network users, though it appears incremental as it builds on existing clustering and ANN approaches.
The authors tackled the problem of determining optimal neural network architecture by proposing a clustering-based construction method for multilayer perceptrons in regression tasks, demonstrating its efficiency across different datasets.
The choice of architecture of artificial neuron network (ANN) is still a challenging task that users face every time. It greatly affects the accuracy of the built network. In fact there is no optimal method that is applicable to various implementations at the same time. In this paper we propose a method to construct ANN based on clustering, that resolves the problems of random and ad hoc approaches for multilayer ANN architecture. Our method can be applied to regression problems. Experimental results obtained with different datasets, reveals the efficiency of our method.