N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

Cortical substrates for exploratory decisions in humans.

Decision making in an uncertain environment poses a conflict between the opposing demands of gathering and exploiting information. In a classic illustration of this 'exploration-exploitation' dilemma, a gambler choosing between multiple slot machines balances the desire to select what seems, on the basis of accumulated experience, the richest option, against the desire to choose a less familiar option that might turn out more advantageous (and thereby provide information for improving future decisions). Far from representing idle curiosity, such exploration is often critical for organisms to discover how best to harvest resources such as food and water. In appetitive choice, substantial experimental evidence, underpinned by computational reinforcement learning (RL) theory, indicates that a dopaminergic, striatal and medial prefrontal network mediates learning to exploit. In contrast, although exploration has been well studied from both theoretical and ethological perspectives, its neural substrates are much less clear. Here we show, in a gambling task, that human subjects' choices can be characterized by a computationally well-regarded strategy for addressing the explore/exploit dilemma. Furthermore, using this characterization to classify decisions as exploratory or exploitative, we employ functional magnetic resonance imaging to show that the frontopolar cortex and intraparietal sulcus are preferentially active during exploratory decisions. In contrast, regions of striatum and ventromedial prefrontal cortex exhibit activity characteristic of an involvement in value-based exploitative decision making. The results suggest a model of action selection under uncertainty that involves switching between exploratory and exploitative behavioural modes, and provide a computationally precise characterization of the contribution of key decision-related brain systems to each of these functions.

多机器人动态编队的强化学习算法研究

在人工智能领域中 ,强化学习理论由于其自学习性和自适应性的优点而得到了广泛关注 随着分布式人工智能中多智能体理论的不断发展 ,分布式强化学习算法逐渐成为研究的重点 首先介绍了强化学习的研究状况 ,然后以多机器人动态编队为研究模型 ,阐述应用分布式强化学习实现多机器人行为控制的方法 应用SOM神经网络对状态空间进行自主划分 ,以加快学习速度 ;应用BP神经网络实现强化学习 ,以增强系统的泛化能力 ;并且采用内、外两个强化信号兼顾机器人的个体利益及整体利益 为了明确控制任务 ,系统使用黑板通信方式进行分层控制 最后由仿真实验证明该方法的有效性

冲压自动生产线上下料机器人示教编程方法

针对由多台机器人及多种辅助设备组成的冲压自动生产线编程量大、运动协调关系复杂、联锁信号多的特点 ,介绍一种离线规划与在线示教相结合的冲压机器人示教编程方法 ,对冲压机器人进行运动轨迹、作业内容等方面的示教 ,降低了示教内容的复杂性 ,节省了在线示教所占用的现场调试和生产时间。

南沙群岛工程地质环境分区与珊瑚礁工程地质特性研究

Nansha Islands as sacred territory of China, containing abundant natural resources is the important area of sustaining development of Chinese people. Safeguarding and developing Nansha Islands has become one important part to develop ocean resource of China in 21 century. Engineering geological problems will be faced inevitably in the processes of engineering construction. Coral reef is a new kind of soil and rock and has special engineering characteristics. This doctoral dissertation researches deeply and systematically the regional engineering geology environmental properties and quality, engineering geological characteristics of coral reefs sand on the basis of synthetic analysis of hydrology, climate, geology, geomorphology and engineering field exploration information and combining the experimental data. 1. Put forward the division program of engineering geological environment of Nansha Islands according to the data of hydrology, geology and sediments, and also deeply study the properties of each division. Evaluate the quality of engineering geological environment by fuzzy mathematics and draw the evaluation map of quality of engineering geological environment. The research work provides background support of engineering geological environment to program of resource development in Nansha Islands. 2. Structures of coral reefs have been analyzed. The model of engineering geological zone has been proposed on the basis of geomorphologic zone and combining the strata and ocean dynamic environment. The engineering construction appropriation of each zone is praised. 3. The physical and mechanical properties of coral sands are researched. The results show that coral sands have high void ratio, non-regular shape, easy grain crushing and large compressibility. Shear-expansion takes place only at very low confining pressure and shear-contraction of volumetric strain occurs at higher confining pressure. Internal friction angle decreases with the increasing of confining pressure. The grain crushing property is the main factor influencing the mechanical characteristics. 4. A revised E-ν constitutive model is proposed which considers the change of internal friction angle with confining pressure, and parameter values are also determined. 5. The stability of Yongshu Reef by is analysed for the purpose of serving engineering struction. The process and mechanism of deformation and failure of foundation and slope is analyzed by finite-element method.

问题解决及学习中的条件认知水平

Learning to recognize the conditions under which actions should be considered is a crucial component in the acquisition of cognitive skill. This research focus on the way in which conditions are recognized during problem solving, so as to design effective material for learning through problem solving. The results of experiment I indicated that the subjects abstracted contents from different resources as condition at structural level through out the whole process of problem solving. The results of experiment 2 indicated that the efficiency of learning through problem solving could be greatly improved by emphasizing the recognization of conditions at structural level. The implications for both theory and application are discussed.

Poly-transformation

King, R. D. and Ouali, M. (2004) Poly-transformation. In proceedings of 5th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2004). Springer LNCS 3177 p99-107

Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001

Toivonen, H., Srinivasan, A., King, R. D., Kramer, S. and Helma, C. (2003) Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001. Bioinformatics 19: 1183-1193

Assessing training and professional development needs of library staff. Report for National Library of Health

Urquhart, C., Spink, S. & Thomas, R., Assessing training and professional development needs of library staff. Report for National Library of Health. (2005). Aberystwyth: Department of Information Studies, University of Wales Aberystwyth Sponsorship: National Library for Health (NHS Information Authority)

Projekty rozwojowe w tubylczej społeczności Meksyku i ich społeczno-kulturowe konsekwencje

Wydział Historyczny

Making Sadza with Deaf Zimbabwean Women: A Missiological Reorientation of Practical Theological Method toward Self-Theologizing Agency among Subaltern Communities

Missiological calls for self-theologizing among faith communities present the field of practical theology with a challenge to develop methodological approaches that address the complexities of cross-cultural, practical theological research. Although a variety of approaches can be considered critical correlative practical theology, existing methods are often built on assumptions that limit their use in subaltern contexts. This study seeks to address these concerns by analyzing existing theological methodologies with sustained attention to a community of Deaf Zimbabwean women struggling to develop their own agency in relation to child rearing practices. This dilemma serves as an entry point to an examination of the limitations of existing methodologies and a constructive, interdisciplinary theological exploration. The use of theological modeling methodology employs my experience of learning to cook sadza, a staple dish of Zimbabwe, as a guide for analyzing and reorienting practical theological methodology. The study explores a variety of theological approaches from practical theology, mission oriented theologians, theology among Deaf communities, and African women’s theology in relationship to the challenges presented by subaltern communities such as Deaf Zimbabwean women. Analysis reveals that although there is much to commend in these existing methodologies, questions about who does the critical correlation, whose interests are guiding the study, and consideration for the cross-cultural and power dynamics between researchers and faith communities remain problematic for developing self-theologizing agency. Rather than frame a comprehensive methodology, this study proposes three attitudes and guideposts to reorient practical theological researchers who wish to engender self-theologizing agency in subaltern communities. The creativity of enacted theology, the humility of using checks and balances in research methods, and the grace of finding strategies to build bridges of commonality and community offer ways to reorient practical theological methodologies toward the development of self-theologizing agency among subaltern people. This study concludes with discussion of how these guideposts can not only benefit particular work with a community of Deaf Zimbabwean women, but also provide research and theological reflection in other subaltern contexts.

Towards a Unified Theory of Neocortex: Laminar Cortical Circuits for Vision and Cognition

A key goal of computational neuroscience is to link brain mechanisms to behavioral functions. The present article describes recent progress towards explaining how laminar neocortical circuits give rise to biological intelligence. These circuits embody two new and revolutionary computational paradigms: Complementary Computing and Laminar Computing. Circuit properties include a novel synthesis of feedforward and feedback processing, of digital and analog processing, and of pre-attentive and attentive processing. This synthesis clarifies the appeal of Bayesian approaches but has a far greater predictive range that naturally extends to self-organizing processes. Examples from vision and cognition are summarized. A LAMINART architecture unifies properties of visual development, learning, perceptual grouping, attention, and 3D vision. A key modeling theme is that the mechanisms which enable development and learning to occur in a stable way imply properties of adult behavior. It is noted how higher-order attentional constraints can influence multiple cortical regions, and how spatial and object attention work together to learn view-invariant object categories. In particular, a form-fitting spatial attentional shroud can allow an emerging view-invariant object category to remain active while multiple view categories are associated with it during sequences of saccadic eye movements. Finally, the chapter summarizes recent work on the LIST PARSE model of cognitive information processing by the laminar circuits of prefrontal cortex. LIST PARSE models the short-term storage of event sequences in working memory, their unitization through learning into sequence, or list, chunks, and their read-out in planned sequential performance that is under volitional control. LIST PARSE provides a laminar embodiment of Item and Order working memories, also called Competitive Queuing models, that have been supported by both psychophysical and neurobiological data. These examples show how variations of a common laminar cortical design can embody properties of visual and cognitive intelligence that seem, at least on the surface, to be mechanistically unrelated.

Identifying sources of global contention in constraint satisfaction search

Much work has been done on learning from failure in search to boost solving of combinatorial problems, such as clause-learning and clause-weighting in boolean satisfiability (SAT), nogood and explanation-based learning, and constraint weighting in constraint satisfaction problems (CSPs). Many of the top solvers in SAT use clause learning to good effect. A similar approach (nogood learning) has not had as large an impact in CSPs. Constraint weighting is a less fine-grained approach where the information learnt gives an approximation as to which variables may be the sources of greatest contention. In this work we present two methods for learning from search using restarts, in order to identify these critical variables prior to solving. Both methods are based on the conflict-directed heuristic (weighted-degree heuristic) introduced by Boussemart et al. and are aimed at producing a better-informed version of the heuristic by gathering information through restarting and probing of the search space prior to solving, while minimizing the overhead of these restarts. We further examine the impact of different sampling strategies and different measurements of contention, and assess different restarting strategies for the heuristic. Finally, two applications for constraint weighting are considered in detail: dynamic constraint satisfaction problems and unary resource scheduling problems.

Is "e-skilling" deskilling?

This paper takes forward the discussion for the development of a Framework for e-Learning. It briefly describes how the discussion has progressed from the suggested development of a Framework and the findings of a study investigating the use of Blended Learning, to the application of PESTE factors from Sociology and the proposal of new PESTE factors for educational software and e-Learning, asking if the current use of Computer-Mediated Communication (CMC) is leading to the deskilling of professions, by the provision of direct, front-line service applications and the implications for e-Learning.

Is "e-skilling e-nabling" or deskilling?

This paper takes forward the discussion for the development of a Framework for e-Learning. It briefly describes how the discussion has progressed from the suggested development of a Framework and the findings of a study investigating the use of Blended Learning, to the application of PESTE factors from Sociology and the proposal of new PESTE factors for educational software and e-Learning, asking if the current use of Computer-Mediated Communication (CMC) is leading to the deskilling of professions, by the provision of direct, front-line service applications and the implications for e-Learning.