When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
In this paper, we investigate the use of parallelization in reinforcement learning (RL), with the goal of learning optimal policies for single-agent RL problems more quickly by us...
Studies have shown that videoconferencing is an effective medium for facilitating communication between parties who are separated by distance, particularly when learners are engag...
In this paper, we propose a recursive method for structural learning of directed acyclic graphs (DAGs), in which a problem of structural learning for a large DAG is first decompos...
Feature selection is often applied to highdimensional data prior to classification learning. Using the same training dataset in both selection and learning can result in socalled ...