Sharif Digital Repository

Superconducting Rapid Single Flux Quantum (RSFQ) Logic, is very fast (up to about THz) and ultra low power circuit technology and is the most recent and fastest superconducting logic family. So far one of the difficulties in RSFQ logic is associated to reading the circuit states in particular flip flops. In prevalent RSFQ logic using T1 Flip Flop gate instead of the T Flip Flop, the non-destructive reading of the registered bit is possible. Through this approach, it also has some limits in particular circuits. Another idea of resolving this issue, is considering the very new bi-directional RSFQ logic, which is based on alternative changing the bias current through the Josephson junctions.... 

Neural Networks have been applied to Language Modeling to solve a major problem that N-gram language models could not overcome: discreteness of the words. Generally, neural networks were successful in solving this problem and improved Language Modeling by reducing the perplexity of the models. Neural networks can find grammatical and semantic connections among the words using word embedding which maps each word to a low dimensional feature vector of real numbers. In this research, different kinds of neural network applied to Language Modeling has been reviewed. Also, it has been tried to reduce the perplexity of Persian language models on a 100-million scale data set using a single-layer...