Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network
This work addresses the challenge of improving unsupervised learning reliability for document classification, though it appears incremental as it combines existing techniques like evolutionary algorithms with neural networks.
The authors tackled the problem of controlling unsupervised learning outcomes in deep neural networks by using an evolutionary algorithm to supervise the process, achieving better accuracy than a traditional supervised classifier on a document classification task.
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled and breeding process selects nodes by calculating degree of their consistency on different sets of sampled data. This method supervises unsupervised training by evolutionary process. We also introduce modified Restricted Boltzmann Machine which contains repulsive force among nodes in a neural network and it contributes to isolate network nodes each other to avoid accidental degeneration of nodes by evolutionary process. These new methods are applied to document classification problem and it results better accuracy than a traditional fully supervised classifier implemented with linear regression algorithm.