Analysis of dropout learning regarded as ensemble learning
This provides a theoretical insight for researchers in machine learning, though it is incremental as it reinterprets an existing method.
The paper tackles the problem of overfitting in deep learning by analyzing dropout learning as a form of ensemble learning, showing that combining neglected units with the learned network can be interpreted in this framework.
Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers, huge number of units, and connections. Therefore, overfitting is a serious problem. To avoid this problem, dropout learning is proposed. Dropout learning neglects some inputs and hidden units in the learning process with a probability, p, and then, the neglected inputs and hidden units are combined with the learned network to express the final output. We find that the process of combining the neglected hidden units with the learned network can be regarded as ensemble learning, so we analyze dropout learning from this point of view.