Neuron-Specific Dropout: A Deterministic Regularization Technique to Prevent Neural Networks from Overfitting & Reduce Dependence on Large Training Samples
This addresses the issue of data scarcity in supervised learning tasks like image recognition, offering a practical solution for scenarios where large datasets are unavailable, though it appears incremental as an enhancement to existing dropout methods.
The paper tackles the problem of deep neural networks requiring large amounts of training data to achieve high accuracy by introducing neuron-specific dropout (NSDropout), a deterministic regularization technique that reduces overfitting and achieves similar or better testing accuracy with far less data than traditional methods like dropout.
In order to develop complex relationships between their inputs and outputs, deep neural networks train and adjust large number of parameters. To make these networks work at high accuracy, vast amounts of data are needed. Sometimes, however, the quantity of data needed is not present or obtainable for training. Neuron-specific dropout (NSDropout) is a tool to address this problem. NSDropout looks at both the training pass, and validation pass, of a layer in a model. By comparing the average values produced by each neuron for each class in a data set, the network is able to drop targeted units. The layer is able to predict what features, or noise, the model is looking at during testing that isn't present when looking at samples from validation. Unlike dropout, the "thinned" networks cannot be "unthinned" for testing. Neuron-specific dropout has proved to achieve similar, if not better, testing accuracy with far less data than traditional methods including dropout and other regularization methods. Experimentation has shown that neuron-specific dropout reduces the chance of a network overfitting and reduces the need for large training samples on supervised learning tasks in image recognition, all while producing best-in-class results.