Abstract. Active learning refers to the task of devising a ranking function that, given a classifier trained from relatively few training examples, ranks a set of additional unlabe...
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for USD/JPY exchange rates forecasting. Previous work often used time series techniques and neural networks (NN...
Meysam Alizadeh, Roy Rada, Akram Khaleghei Ghoshe ...
This study tries to find the designing blind spots of the voice prompt function in the current car navigation systems and make improvement suggestions. The experimental plan was im...
The lack of good "correlation" between pre-silicon simulated delays and measured delays on silicon (silicon data) has spurred efforts on so-called silicon debug. The ide...