AdaNet: Adaptive Structural Learning of Artificial Neural Networks
This addresses the challenge of manual network design for practitioners, though it appears incremental as it builds on existing neural network methods.
The paper tackles the problem of automatically learning both the structure and weights of artificial neural networks, achieving competitive performance accuracies on binary classification tasks from CIFAR-10 compared to standard approaches.
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.