基于模糊聚类的神经网络求解围棋死活博弈

围棋死活求解非常消耗计算资源,博弈树的节点数随分支因子和深度的增加而呈指数级增长,使得传统的完全遍历博弈树的搜索不足以胜任.文中提出了一种基于模糊聚类的神经网络方法,利用模式识别和模糊属性检测,为涉及到外部劫争、循环规避、哈希置换、证明树等多方面问题的围棋博弈死活求解,构建了基于神经网络的棋型聚类分析器,快速又有效地极大减小了博弈树的分支因子,节约了死活求解所耗费的计算时间和内存空间.实验证明取得了比较理想的结果,研究表明把自学习能力赋予程序是提高计算机围棋博弈性能的有效途径.     

围棋死活问题的计算机求解

提出了一种基于搜索的围棋死活问题的求解方法，并实现了一个围棋死活问题求解程序SharpSense。对比实验表明，SharpSense的性能明显优于同类程序，对封闭围棋死活问题的解题能力达到了围棋专业棋手的水平。SharpSense还发现了围棋死活问题经典著作《围棋死活大全》中的两个错误。     

Grab and Go Systems: a CPO approach to concurrent web and grid-based computation

A useful property of web–based information systems [1] is the ability to display partial information. For example, a web program can display a sequence of fuzzy images which is extended by the production of improved images as execution of the program proceeds. A sequence of improving approximations to an image can be modelled by the elements of a complete partial order (CPO). CPOs can also be used to model grid-based computations. For example, consider a collection of iterative processes, each with identical functionality, which individually generate a series of improving approximations towards a desired goal. Sharing approximations from time to time among the processes may produce faster convergence than could be achieved by any of the processes separately. Each process in the collection has the potential to exchange partial information with its companions so that all may make use of the best information available.In this paper a non-blocking communication abstraction, based on CPOs, is used to develop a model of iterative web- and grid-based computations. The abstraction is novel in that it may not directly match a send communication in one process with a corresponding receive communication in another; rather, a receive communication is identified with taking the least upper bound of the set of messages available at an input port - this set may be empty, contain exactly one messsage or contain multiple messages. In all cases the receiver does not wait but gathers the best available information and proceeds with its computation. Thus, the abstraction corresponds to a loosely coupled model of distributed computation. The applicability of the model is illustrated by a number of disparate examples of distributed iterative computation.     

Learning and the quality of working life

Improving the quality of working life is now recognized as a learning process. It is one, moreover, which engages our full potential for extracting information from the environment and putting it to work for common-sense purposes. The learning shown by participants in genuinely participative QWL projects conflicts however with many of the assumptions of traditional education and the role of experts. The paper examines this conflict as it may appear in a QWL project and argues for the whole-hearted common-sense approach which leads to envolving democratically structured workplaces. At stake is the energy and motivation for change, particularly in times of economic downturn.     

Learning Bayesian networks using various datasources and applications to financial analysis

 This paper illustrates opportunities of using Bayesian networks in fundamental financial analysis. In it, we will present an application based on construction of a Bayesian network from a database of financial reports collected for the years 1993–97. We will focus on one sector of the Czech economy – engineering – presenting an example that use the constructed Bayesian network in the sector financial analysis. In addition, we will deal with the rating analysis and show how to perform this kind of analysis by means of neural and Bayesian networks. This work was supported by the grant VS96008 of the Ministry of Education of the Czech Republic.     

Using Neural Networks to predict HFACS unsafe acts from the pre-conditions of unsafe acts

Abstract

Human Factors Analysis and Classification System (HFACS) is based upon Reason’s organizational model of human error which suggests that there is a ‘one to many’ mapping of condition tokens (HFACS level 2 psychological precursors) to unsafe act tokens (HFACS level 1 error and violations). Using accident data derived from 523 military aircraft accidents, the relationship between HFACS level 2 preconditions and level 1 unsafe acts was modelled using an artificial neural network (NN). This allowed an empirical model to be developed congruent with the underlying theory of HFACS. The NN solution produced an average overall classification rate of ca. 74% for all unsafe acts from information derived from their level 2 preconditions. However, the correct classification rate was superior for decision- and skill-based errors, than for perceptual errors and violations.

Practitioner Summary: A model to predict unsafe acts (HFACS level 1) from their preconditions (HFACS level 2) was developed from the analysis of 523 military aircraft accidents using an artificial NN. The results could correctly predict approximately 74% of errors.     

PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g. jets or MLS surfaces), local or non-local averaging or on statistical assumptions about the underlying noise model. In contrast, we develop a simple data-driven method for removing outliers and reducing noise in unordered point clouds. We base our approach on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Our method first classifies and discards outlier samples, and then estimates correction vectors that project noisy points onto the original clean surfaces. The approach is efficient and robust to varying amounts of noise and outliers, while being able to handle large densely sampled point clouds. In our extensive evaluation, both on synthetic and real data, we show an increased robustness to strong noise levels compared to various state-of-the-art methods, enabling accurate surface reconstruction from extremely noisy real data obtained by range scans. Finally, the simplicity and universality of our approach makes it very easy to integrate in any existing geometry processing pipeline. Both the code and pre-trained networks can be found on the project page ( https://github.com/mrakotosaon/pointcleannet ).     

Learning to trust in the competence and commitment of agents

For agents to collaborate in open multi-agent systems, each agent must trust in the other agents’ ability to complete tasks and willingness to cooperate. Agents need to decide between cooperative and opportunistic behavior based on their assessment of another agents’ trustworthiness. In particular, an agent can have two beliefs about a potential partner that tend to indicate trustworthiness: that the partner is competent and that the partner expects to engage in future interactions. This paper explores an approach that models competence as an agent’s probability of successfully performing an action, and models belief in future interactions as a discount factor. We evaluate the underlying decision framework’s performance given accurate knowledge of the model’s parameters in an evolutionary game setting. We then introduce a game-theoretic framework in which an agent can learn a model of another agent online, using the Harsanyi transformation. The learning agents evaluate a set of competing hypotheses about another agent during the simulated play of an indefinitely repeated game. The Harsanyi strategy is shown to demonstrate robust and successful online play against a variety of static, classic, and learning strategies in a variable-payoff Iterated Prisoner’s Dilemma setting.     

P- and SV-wave separation by polarization-dependent velocity filtering: application to vertical seismic profiles from Kola superdeep borehole, Russia

In multicomponent seismic surveys, separation of interfering compressional (P) and shear-wave (S) energy provides valuable information for the interpretation of mode conversions and seismic anisotropy. We present a technique for such a separation using a polarization-dependent velocity filtering. At the first step of the procedure, a linear two-channel filter is designed in the frequency-wavenumber domain, with filter coefficients determined by the angles of incidence of respective seismic waves. Due to several physical reasons, the filter is unstable near the high end of the P-wave spectrum. We stabilize the filter with the use of S-wave spectrum balancing. This operation results in a robust decomposition into P- and SV-responses, while retaining the full energy of the vector wavefield. We implement this method in a module of our seismic processing system. The module employs a versatile parametrization scheme, as well as structured data input/output. It is able to process VSP or surface data, with velocities varying by either depth or offset. Application of the module to the processing of an offset VSP from the Kola Superdeep Borehole demonstrates that the program successfully separates P- and S-wave phases in crustal VSP data.     

An immersive virtual reality serious game to enhance earthquake behavioral responses and post-earthquake evacuation preparedness in buildings

Enhancing the earthquake behavioral responses and post-earthquake evacuation preparedness of building occupants is beneficial to increasing their chances of survival and reducing casualties after the mainshock of an earthquake. Traditionally, training approaches such as seminars, posters, videos or drills are applied to enhance preparedness. However, they are not highly engaging and have limited sensory capabilities to mimic life-threatening scenarios for the purpose of training potential participants. Immersive Virtual Reality (IVR) and Serious Games (SG) as innovative digital technologies can be used to create training tools to overcome these limitations. In this study, we propose an IVR SG-based training system to improve earthquake behavioral responses and post-earthquake evacuation preparedness. Auckland City Hospital was chosen as a case study to test our IVR SG training system. A set of training objectives based on best evacuation practice has been identified and embedded into several training scenarios of the IVR SG. Hospital staff (healthcare and administrative professionals) and visitors were recruited as participants to be exposed to these training scenarios. Participants’ preparedness has been measured along two dimensions: 1) Knowledge about best evacuation practice; 2) Self-efficacy in dealing with earthquake emergencies. Assessment results showed that there was a significant knowledge and self-efficacy increase after the training. In addition, participants acknowledged that it was easy, helpful, and engaging to learn best evacuation practice knowledge through the IVR SG training system.     

Exploring Different Parameters to Assess Left Ventricle Global and Regional Functional Analysis from Coronary CT Angiography

Coronary CT angiography is widely used in clinical practice for the assessment of coronary artery disease. Several studies have shown that the same exam can also be used to assess left ventricle (LV) function. Even though coronary CT angiography provides data concerning multiple cardiac phases, along the cardiac cycle, LV function is usually evaluated using just the end‐systolic and end‐diastolic phases. This unused wealth of data, mostly due to its complexity and the lack of proper tools, has still to be explored to assess if further insight is possible regarding regional LV functional analysis. Furthermore, different parameters can be computed to characterize LV function and though some are well known by clinicians others still need to be tested concerning their value in clinical scenarios. Based on these premises, we present several parameters characterizing global and regional LV function, computed for several cardiac phases over one cardiac cycle. The data provided by the computed parameters is shown using a set of visualizations allowing synchronized visual exploration of the different data. The main purpose is to provide means for clinicians to explore the data and gather insight over their meaning and their correlation with each other and with diagnosis outcomes.