We propose a new sampling method for 2D and 3D implicit surfaces. The method is based on a stochastic process defined by the Langevin equation with a Gaussian random-force term. Our Langevin equation describes a stochastic-dynamical particle, which develops in time confined around the sampled implicit surface with small width. Its numerically generated solutions can be easily moved onto the surface strictly with very few iteration of the Newton correction. The method is robust in a sense that an arbitrary number of sample points can be obtained starting from one simple initial condition. It is because (1) the time development of the stochastic-dynamical particle does not terminate even when it reaches the sampled implicit surface, and (2) there is non-zero transition probability from one disconnected component to another. The method works very well for implicit surfaces which are complicated topologically, mathematically, and/or in shape. It also has some advantageous features in rendering 3D implicit surfaces. Many examples of applying our sampling method to real 2D and 3D implicit surfaces are presented.

Automated information extraction systems from biomedical text have been reported. Some systems are based on manually developed rules or pattern matching. Manually developed rules are specific for analysis, however, new rules must be developed for each new domain. Although the corpus must be developed by human effort, a machine-learning approach automatically learns the rules from the corpus. In this article, we present a system for automatically extracting protein-protein interaction information from biomedical text with support vector machines (SVMs). We describe the performance of our system and compare its ability to extract protein-protein interaction information with that of other systems.

In an IoT system, neural networks have the potential to perform advanced information processing in various environments. To clarify this, the robustness of a restricted Boltzmann machine (RBM) used for deep neural networks, such as a deep belief network (DBN), was studied in this paper. Even if memory or logic errors occurred in the circuit operating in the RBM while pre-training the DBN, they did not affect the identification rate of the DBN, showing the robustness of the RBM. In addition, robustness against soft errors was evaluated. The soft errors had almost no influence on the RBM unless they were as large as 1012 times or more in the 50-nm CMOS process.