Binary Stochastic Filtering: a Method for Neural Network Size Minimization and Supervised Feature Selection
This addresses the problem of computational efficiency and feature selection for machine learning practitioners, though it appears incremental as it builds on existing pruning and filtering techniques.
The paper tackles the problem of neural network size minimization and supervised feature selection by proposing Binary Stochastic Filtering (BSF), which stochastically filters features or neurons during training, achieving a multifold decrease in network size and surpassing literature references in accuracy/dimensionality ratio.
Binary Stochastic Filtering (BSF), the algorithm for feature selection and neuron pruning is proposed in this work. The method defines filtering layer which penalizes amount of the information involved in the training process. This information could be the input data or output of the previous layer, which directly leads to the feature selection or neuron pruning respectively, producing \textit{ad hoc} subset of features or selecting optimal number of neurons in each layer. Filtering layer stochastically passes or drops features based on individual weights, which are tuned with standard backpropagation algorithm during the training process. Multifold decrease of neural network size has been achieved in the experiments. Besides, the method was able to select minimal number of features, surpassing literature references by the accuracy/dimensionality ratio.