A Hybrid Neural Network Approach to Estimate Galaxy Redshifts from Multi-Band Photometric Surveys

Machine learning methods have been used in cosmological studies to estimate variables that would be hard or costly to measure precisely, like, for example, estimating redshifts from photometric data. Previous work showed good results for estimating photometric redshifts using nonlinear regression based on an artificial neural network (MultiLayer Perceptron or MLP). In this work we explore a hybrid neural network approach that uses a Self-Organizing Map (SOM) to separate the original data into different groups, then applying the MLP to each neuron on the SOM to obtain different regression models for each group. Preliminary results indicate that in some cases better results can be achieved, although the computational cost may be increased.