Threshold agent networks (TANs) constitute a discretized modification of threshold (also known as neural) networks that are appropriate for modeling computer simulations. In this p...
Today there is a relatively large body of work on automatic acquisition of lexicosyntactical preferences (subcategorization) from corpora. Various techniques have been developed t...
Illumination variation that occurs on face images degrades the performance of face recognition. In this paper, we propose a novel approach to handling illumination variation for f...
This paper proposes a fast and simple unsupervised word segmentation algorithm that utilizes the local predictability of adjacent character sequences, while searching for a leaste...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...