Rough Deep Belief Network - Application to Incomplete Handwritten Digits Pattern Classification
Wojciech K. Mleczko, Tomasz Kapuściński, Robert K. Nowicki · Communications in computer and information science · 2015
The rough deep belief networks (RDBN) are new modification of well known deep belief networks. Thanks to applied elements from Pawlak’s rough set theory, RDBNs are suitable in processing of incomplete patterns. In this paper we present the results of adaptation of this class of networks for classification of handwritten digits. The samples of the pattern applied in the learning and working processes are randomly corrupted. This allows to study the robustness of classifier for various levels of incompleteness.