Regularization for Unsupervised Deep Neural Nets
This addresses overfitting issues in unsupervised deep learning models, which is an incremental improvement for researchers and practitioners in machine learning.
The paper tackles overfitting in unsupervised neural networks like RBMs and DBNs, proposing regularization methods including a 'partial' approach to improve Dropout/DropConnect efficiency, and shows results through likelihood and classification error rates on pattern recognition datasets.
Unsupervised neural networks, such as restricted Boltzmann machines (RBMs) and deep belief networks (DBNs), are powerful tools for feature selection and pattern recognition tasks. We demonstrate that overfitting occurs in such models just as in deep feedforward neural networks, and discuss possible regularization methods to reduce overfitting. We also propose a "partial" approach to improve the efficiency of Dropout/DropConnect in this scenario, and discuss the theoretical justification of these methods from model convergence and likelihood bounds. Finally, we compare the performance of these methods based on their likelihood and classification error rates for various pattern recognition data sets.