The Self-Organizing Restricted Boltzmann Machine for Deep Representation with the Application on Classification Problems

• Published in: Expert systems with applications 2020-07, Vol.149, p.113286, Article 113286
• Main Authors: Pirmoradi, Saeed, Teshnehlab, Mohammad, Zarghami, Nosratollah, Sharifi, Arash
• Format: Article
• Language: English
• Subjects: Algorithms; Belief networks; Computer architecture; Correlation analysis; Deep learning; Machine learning; MNIST; Model accuracy; Moore-set; Neurons; Regularization; Regularization methods; Representations; Self-organizing restricted Boltzmann machines; Separability-correlation measure; Wisconsin breast cancer dataset
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2020.113286

•The proposed approach can determine number of hidden layers in DBN and hidden neurons in RBM.•It removes the need of trial and error for discovering the reasonable (or optimal) network structure.•It is low cost from terms of time and computation.•It is the self-organizing deep model.•It acts as a regularization method and prevents over-fitting. Recently, deep learning is proliferating in the field of representation learning. A deep belief network (DBN) consists of a deep network architecture that can generate multiple features of input patterns, using restricted Boltzmann machines (RBMs) as a building block of DBN. A deep learning model can achieve extremely high accuracy in many applications that depend on the model structure. However, specifying various parameters of deep network architecture like the number of hidden layers and neurons is a difficult task even for expert designers. Besides, the number of hidden layers and neurons is typically set manually, while this method is costly in terms of time and computational cost, especially in big data. In this paper, we introduce an approach to determine the number of hidden layers and neurons of the deep network automatically during the learning process. To this end, the input vector is transformed from the feature space with a low dimension into the new feature space with a high dimension in a hidden layer of RBM. In the following, new features are ranked according to their discrimination power between classes in the new space, using the Separability-correlation measure for feature importance ranking algorithm. The algorithm uses the mean of weights as a threshold, so the neurons whose weights exceed the threshold are retained, and the others are removed in the hidden layer. The number of retained neurons is presented as a reasonable number of neurons. The number of layers is also determined in the deep model, using the validation data. The proposed approach acts as a regularization method since the neurons whose weights are lower than the threshold are removed; thus, RBM learns to copy input merely approximate. It also prevents over-fitting with a suitable number of hidden layers and neurons. Eventually, DBN can determine its structure according to the input data and is the self-organizing model. The experimental results on benchmark datasets confirm the proposed method.