Improved Classification Based on Deep Belief Networks
This work addresses the need for more efficient and effective classification methods in machine learning, though it appears incremental as it builds on existing deep belief network frameworks.
The paper tackled the problem of improving classification by integrating unsupervised and supervised learning phases in deep belief networks, resulting in models that outperform the traditional two-phase training approach.
For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learning. We developed several supervised models based on DBN in order to improve this two-phase strategy. Modifying the loss function to account for expectation with respect to the underlying generative model, introducing weight bounds, and multi-level programming are applied in model development. The proposed models capture both unsupervised and supervised objectives effectively. The computational study verifies that our models perform better than the two-phase training approach.