Gradual Training Method for Denoising Auto Encoders
This incremental improvement addresses training efficiency for deep networks on mid-sized datasets.
The paper tackled training deep denoising autoencoders by introducing a gradual training method where layers are added incrementally, resulting in small but consistent improvements in reconstruction quality and classification error on MNIST and CIFAR datasets.
Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets.