Farhad Abedini - Faculty of Computer and Information Technology Engineering، Qazvin Branch، Islamic Azad University، Qazvin، Iran
Mohammad Bagher Menhaj - Department of Computer Engineering،Amirkabir University of Technology، Tehran، Iran
Mohammad Reza Keyvanpour - Department of Computer Engineering،Alzahra University،Vanak،Tehran، Iran

In this paper، a state-of-the-art neuron mathematical model of neural tensor network (NTN) is proposed to RDF knowledge base completion problem. One of the difficulties with the parameter of the network is that representation of its neuron mathematical model is not possible. For this reason، the NTN is modeled as a multi-layer perceptron (MLP) network and the tensor parameter can be distributed into the new network neurons. Moreover، it is suggested that the inputs can be converted into one vector rather than the inputs of NTN are two correlated vectors at the same time،The results approve that the NTN dose not indeed represent a new neural network and the implementation results easily confirm it can be considered as another represention of the MLP network. So، the first idea is represention of a neuron based mathematical model for the NTN through the ordinary and yet well-defined neural network concepts and next contribution will be equivalency proof of the two NTN and suggested MLP networks.

Semantic Web، Knowledgebase Completion، Neural Tensor Network، Multi-Layer Perceptron Network، RDF Data Model