A novel character-level neural language model is proposed in this paper. The proposed model incorporates a biologically inspired temporal hierarchy in the architecture for representing multiple compositions of language in order to handle longer sequences for the character-level language model. The temporal hierarchy is introduced in the language model by utilizing a Gated Recurrent Neural Network with multiple timescales. The proposed model incorporates a timescale adaptation mechanism for enhancing the performance of the language model. We evaluate our proposed model using the popular Penn Treebank and Text8 corpora. The experiments show that the use of multiple timescales in a Neural Language Model (NLM) enables improved performance despite having fewer parameters and with no additional computation requirements. Our experiments also demonstrate the ability of the adaptive temporal hierarchies to represent multiple compositonality without the help of complex hierarchical architectures and shows that better representation of the longer sequences lead to enhanced performance of the probabilistic language model.

No abstract

Aircraft radar has special function which is ranging from aircraft to ground of antenna boresight. Because ranging information is used to calibrate altitude of aircraft or to drop a conventional bomb, the measuring have to be precise and robust. Therefore, we propose a simple and efficient method using monopulse radar for ground ranging. Proposed method calculates balancing weight according to linearity of monopulse ratio and mixes two ranging measurements in proportional to the weight. By exploiting balancing weight, radar is able to react to various environment as monopulse ratio contains characteristics of clutter environment. As a result, robust ranging information can be achieved. We use DEM(Digital Elevation Model) in order to simulate heterogeneous environment. In experimental result, it is shown that proposed method shows better accuracy and precision in any environment.

No abstract