With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
We introduce a novel training algorithm for unsupervised grammar induction, called Zoomed Learning. Given a training set T and a test set S, the goal of our algorithm is to identi...
Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...
In this paper, we demonstrate a novel landmark photo search and browsing system, Agate, which ranks landmark image search results considering their relevance, diversity and qualit...
Yuheng Ren, Mo Yu, Xin-Jing Wang, Lei Zhang, Wei-Y...
Prediction suffix trees (PST) provide a popular and effective tool for tasks such as compression, classification, and language modeling. In this paper we take a decision theoretic...