We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including data-dependent generalization guarantees that we prove and discuss in detail. We report the results of large-scale experiments with one of our algorithms on several binary classification tasks extracted from the CIFAR-10 dataset. The results demonstrate that our algorithm can automatically learn network structures with very competitive performance accuracies when compared with those achieved for neural networks found by standard approaches.
@article{arxiv.1607.01097,
title = {AdaNet: Adaptive Structural Learning of Artificial Neural Networks},
author = {Corinna Cortes and Xavi Gonzalvo and Vitaly Kuznetsov and Mehryar Mohri and Scott Yang},
journal= {arXiv preprint arXiv:1607.01097},
year = {2017}
}