Learning Compact Convolutional Neural Networks with Nested Dropout
This work addresses the problem of model compression and efficiency for machine learning practitioners, but it is incremental as it extends an existing method to a new architecture.
The paper investigates applying nested dropout to convolutional neural networks to determine optimal representation size based on accuracy and task complexity, showing it can effectively order units by information content without degrading performance.
Recently, nested dropout was proposed as a method for ordering representation units in autoencoders by their information content, without diminishing reconstruction cost. However, it has only been applied to training fully-connected autoencoders in an unsupervised setting. We explore the impact of nested dropout on the convolutional layers in a CNN trained by backpropagation, investigating whether nested dropout can provide a simple and systematic way to determine the optimal representation size with respect to the desired accuracy and desired task and data complexity.