Extracting and inserting knowledge into stacked denoising auto-encoders

Abstract

Deep neural networks (DNNs) with a complex structure and multiple nonlinear processing units have achieved great successes for feature learning in image and visualization analysis. Due to interpretability of the “black box” problem in DNNs, however, there are still many obstacles to applications of DNNs in various real-world cases. This paper proposes a new DNN model, knowledge-based deep stacked denoising auto-encoders (KBSDAE), which inserts the knowledge (i.e., confidence and classification rules) into the deep network structure. This model not only can offer a good understanding of the representations learned by the deep network but also can produce an improvement in the learning performance of stacked denoising auto-encoder (SDAE). The knowledge discovery algorithm is proposed to extract confidence rules to interpret the layerwise network (i.e., denoising auto-encoder (DAE)). The symbolic language is developed to describe the deep network and shows that it is suitable for the representation of quantitative reasoning in a deep network. The confidence rule insertion to the deep network is able to produce an improvement in feature learning of DAEs. The classification rules extracted from the data offer a novel method for knowledge insertion to the classification layer of SDAE. The testing results of KBSDAE on various benchmark data indicate that the proposed method not only effectively extracts knowledge from the deep network, but also shows better feature learning performance than that of those typical DNNs (e.g., SDAE).