The Semi-Parallel Deep Neural Network (SPDNN) idea is explained in this article and it has been shown that the convergence of the mixed network is very close to the best network in the set and the generalization of SPDNN is better than all the parent networks.
@article{arxiv.1711.01963,
title = {Semi-Parallel Deep Neural Networks (SPDNN), Convergence and Generalization},
author = {Shabab Bazrafkan and Peter Corcoran},
journal= {arXiv preprint arXiv:1711.01963},
year = {2017}
}