Effects of the user model on simulation-based learning of dialogue strategies

Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to which strategies learned with a user model generalise to real user populations has not be investigated. This paper presents a series of experiments that qualitatively and quantitatively examine the effect of the user model on the learned strategy. Our results show that the performance and characteristics of the strategy are in fact highly dependent on the user model. Furthermore, a policy trained with a poor user model may appear to perform well when tested with the same model, but fail when tested with a more sophisticated user model. This raises significant doubts about the current practice of learning and evaluating strategies with the same user model. The paper further investigates a new technique for testing and comparing strategies directly on real human-machine dialogues, thereby avoiding any evaluation bias introduced by the user model. © 2005 IEEE.

Conservation strategies for endemic fish species threatened by the Three Gorges Dam

The largest damming project to date, the Three Gorges Dam has been built along the Yangtze River (China), the most species-rich river in the Palearctic region. Among 162 species of fish inhabiting the main channel of the upper Yangtze, 44 are endemic and are therefore under serious threat of global extinction from the dam. Accordingly, it is urgently necessary to develop strategies to minimize the impacts of the drastic environmental changes associated with the dam. We sought to identify potential reserves for the endemic species among the 17 tributaries in the upper Yangtze, based on presence/absence data for the 44 endemic species. Potential reserves for the endemic species were identified by characterizing the distribution patterns of endemic species with an adaptive learning algorithm called a "self-organizing map" (SOM). Using this method, we also predicted occurrence probabilities of species in potential reserves based on the distribution patterns of communities. Considering both SOM model results and actual knowledge of the biology of the considered species, our results suggested that 24 species may survive in the tributaries, 14 have an uncertain future, and 6 have a high probability of becoming extinct after dam filling.

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.

A Self-Organizing Neural Network for Learning a Body-Centered Invariant Representation of 3-D Target Position

This paper describes a self-organizing neural network that rapidly learns a body-centered representation of 3-D target positions. This representation remains invariant under head and eye movements, and is a key component of sensory-motor systems for producing motor equivalent reaches to targets (Bullock, Grossberg, and Guenther, 1993).

Sequential Memory with ART: A Self-Organizing Network Capable of Learning Sequences of Patterns

A model which extends the adaptive resonance theory model to sequential memory is presented. This new model learns sequences of events and recalls a sequence when presented with parts of the sequence. A sequence can have repeated events and different sequences can share events. The ART model is modified by creating interconnected sublayers within ART's F2 layer. Nodes within F2 learn temporal patterns by forming recency gradients within LTM. Versions of the ART model like ART I, ART 2, and fuzzy ART can be used.

From Synapse to Self: Spikes, Synchrony, and Attentive Learning by Laminar Thalamocortical Circuits

How do our brains transform the "blooming buzzing confusion" of daily experience into a coherent sense of self that can learn and selectively attend to important information? How do local signals at multiple processing stages, none of which has a global view of brain dynamics or behavioral outcomes, trigger learning at multiple synaptic sites when appropriate, and prevent learning when inappropriate, to achieve useful behavioral goals in a continually changing world? How does the brain allow synaptic plasticity at a remarkably rapid rate, as anyone who has gone to an exciting movie is readily aware, yet also protect useful memories from catastrophic forgetting? A neural model provides a unified answer by explaining and quantitatively simulating data about single cell biophysics and neurophysiology, laminar neuroanatomy, aggregate cell recordings (current-source densities, local field potentials), large-scale oscillations (beta, gamma), and spike-timing dependent plasticity, and functionally linking them all to cognitive information processing requirements.

ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network

This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This supervised learning system is built up from a pair of Adaptive Resonance Theory modules (ARTa and ARTb) that are capable of self-organizing stable recognition categories in response to arbitrary sequences of input patterns. During training trials, the ARTa module receives a stream {a^(p)} of input patterns, and ARTb receives a stream {b^(p)} of input patterns, where b^(p) is the correct prediction given a^(p). These ART modules are linked by an associative learning network and an internal controller that ensures autonomous system operation in real time. During test trials, the remaining patterns a^(p) are presented without b^(p), and their predictions at ARTb are compared with b^(p). Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms, and achieves 100% accuracy after training on less than half the input patterns in the database. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. This computation increases the vigilance parameter ρa of ARTa by the minimal amount needed to correct a predictive error at ARTb· Parameter ρa calibrates the minimum confidence that ARTa must have in a category, or hypothesis, activated by an input a^(p) in order for ARTa to accept that category, rather than search for a better one through an automatically controlled process of hypothesis testing. Parameter ρa is compared with the degree of match between a^(p) and the top-down learned expectation, or prototype, that is read-out subsequent to activation of an ARTa category. Search occurs if the degree of match is less than ρa. ARTMAP is hereby a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success. As a result, rare but important events can be quickly and sharply distinguished even if they are similar to frequent events with different consequences. Between input trials ρa relaxes to a baseline vigilance pa When ρa is large, the system runs in a conservative mode, wherein predictions are made only if the system is confident of the outcome. Very few false-alarm errors then occur at any stage of learning, yet the system reaches asymptote with no loss of speed. Because ARTMAP learning is self stabilizing, it can continue learning one or more databases, without degrading its corpus of memories, until its full memory capacity is utilized.

Vector Associative Maps: Unsupervised Real-time Error-based Learning and Control of Movement Trajectories

This article describes neural network models for adaptive control of arm movement trajectories during visually guided reaching and, more generally, a framework for unsupervised real-time error-based learning. The models clarify how a child, or untrained robot, can learn to reach for objects that it sees. Piaget has provided basic insights with his concept of a circular reaction: As an infant makes internally generated movements of its hand, the eyes automatically follow this motion. A transformation is learned between the visual representation of hand position and the motor representation of hand position. Learning of this transformation eventually enables the child to accurately reach for visually detected targets. Grossberg and Kuperstein have shown how the eye movement system can use visual error signals to correct movement parameters via cerebellar learning. Here it is shown how endogenously generated arm movements lead to adaptive tuning of arm control parameters. These movements also activate the target position representations that are used to learn the visuo-motor transformation that controls visually guided reaching. The AVITE model presented here is an adaptive neural circuit based on the Vector Integration to Endpoint (VITE) model for arm and speech trajectory generation of Bullock and Grossberg. In the VITE model, a Target Position Command (TPC) represents the location of the desired target. The Present Position Command (PPC) encodes the present hand-arm configuration. The Difference Vector (DV) population continuously.computes the difference between the PPC and the TPC. A speed-controlling GO signal multiplies DV output. The PPC integrates the (DV)·(GO) product and generates an outflow command to the arm. Integration at the PPC continues at a rate dependent on GO signal size until the DV reaches zero, at which time the PPC equals the TPC. The AVITE model explains how self-consistent TPC and PPC coordinates are autonomously generated and learned. Learning of AVITE parameters is regulated by activation of a self-regulating Endogenous Random Generator (ERG) of training vectors. Each vector is integrated at the PPC, giving rise to a movement command. The generation of each vector induces a complementary postural phase during which ERG output stops and learning occurs. Then a new vector is generated and the cycle is repeated. This cyclic, biphasic behavior is controlled by a specialized gated dipole circuit. ERG output autonomously stops in such a way that, across trials, a broad sample of workspace target positions is generated. When the ERG shuts off, a modulator gate opens, copying the PPC into the TPC. Learning of a transformation from TPC to PPC occurs using the DV as an error signal that is zeroed due to learning. This learning scheme is called a Vector Associative Map, or VAM. The VAM model is a general-purpose device for autonomous real-time error-based learning and performance of associative maps. The DV stage serves the dual function of reading out new TPCs during performance and reading in new adaptive weights during learning, without a disruption of real-time operation. YAMs thus provide an on-line unsupervised alternative to the off-line properties of supervised error-correction learning algorithms. YAMs and VAM cascades for learning motor-to-motor and spatial-to-motor maps are described. YAM models and Adaptive Resonance Theory (ART) models exhibit complementary matching, learning, and performance properties that together provide a foundation for designing a total sensory-cognitive and cognitive-motor autonomous system.

Learning and practising supply chain management strategies from a business simulation game: a comprehensive supply chain simulation

An Internet based supply chain simulation game (ISCS) is introduced and demonstrated in this paper. Different from other games and extended from the Beer Game, a comprehensive set of supply chain (SC) management strategies can be tested in the game, and these strategies can be evaluated and appraised based on the built-in Management Information System (MIS). The key functionalities of ISCS are designed to increase players SC awareness, facilitate understanding on various SC strategies and challenges, foster collaboration between partners, and improve problem solving skills. It is concluded that an ISCS can be used as an efficient and effective teaching tool as well as a research tool in operations research and management science. Problems and obstacles have been observed while engaging in the SC business scenario game. The actions proposed and implemented to solve these problems have resulted in improved SC performance.

Self-Management of Chronic Pain: Interventions, Strategies, Barriers, and Facilitators

Background & Purpose: Chronic pain is a prevalent chronic condition for which the best management options rarely provide complete relief. Individuals with chronic pain with neuropathic characteristics (NC) report more severe pain and experience less relief from interventions. Little is known about current self-management practices. The purpose of this dissertation was to inform self-management of chronic pain with and without NC at the individual, health system, and policy levels using the Innovative Care for Chronic Conditions Framework. Methods: The study included a systematic search and review and cross-sectional survey. The review evaluated the evidence for chronic pain self-management interventions and explored the role of health care providers in supporting self-management. The survey was mailed to 8,000 randomly selected Canadians in November 2011, and non-respondents were followed-up in May 2012. Screening questions were included for both chronic pain and NC. The questionnaire captured pain descriptions, self-management strategies, and self-management barriers, and facilitators. Results: Findings of the review suggested that self-management interventions are effective in improving pain and health outcomes. Health care professionals provided self-management advice and referred individuals to self-management interventions. The questionnaire was completed by 1,520 Canadians. Those with chronic pain (n=710) identified primary care physicians as the most helpful pain management professional. Overall, use of non-pharmaceutical medical self-management strategies was low. While use positive emotional self-management strategies was high, individuals with NC were more likely to use negative emotional self-management strategies compared to those without NC. Multiple self-management barriers and facilitators were identified, however those with NC were more likely than those without NC to experience low self-efficacy, depression and severe pain which may impair the ability to self-management. Conclusions: Health care professionals have the opportunity to improve chronic pain outcomes by providing self-management advice, referring to self-management interventions, and addressing self-management barriers and facilitators. Individuals with NC may require additional health services to address their greater self-management challenges, and further research is needed to identify non-pharmaceutical interventions effective in relieving chronic pain with NC. Public policy is needed to facilitate health systems in providing long-term self-management support for individuals with chronic pain.

Non-agrocultural co-peratives and economy transformation in Cuba: politic processes and strategies

Contribution of co-operatives has been demonstrated since the 1970s as the main development line in agricultural production in Cuba. In contrast, there has been a late recognition of urban co-operatives, even if the need of transformations based on the realization of property in different territorial scenarios had been identified. The article analyses the reform processes launched since the first decade of the 21st century focusing on the nature of the initiatives fostering formation and promotion of nonagricultural co-operatives including follow up of their performance. The potential and limitations of the recent experiences are examined in order to reflect on the organizational processes and transformations from the point of view of their members. To conclude, some questions are posed about whether these co-operatives are capable of avoiding the impact of earlier employment circumstances and of developing strategies aimed at reinforcing voluntary membership and autonomy on which they are founded.

Learning soft computing control strategies in a modular neural network architecture

Modelling and control of nonlinear dynamical systems is a challenging problem since the dynamics of such systems change over their parameter space. Conventional methodologies for designing nonlinear control laws, such as gain scheduling, are effective because the designer partitions the overall complex control into a number of simpler sub-tasks. This paper describes a new genetic algorithm based method for the design of a modular neural network (MNN) control architecture that learns such partitions of an overall complex control task. Here a chromosome represents both the structure and parameters of an individual neural network in the MNN controller and a hierarchical fuzzy approach is used to select the chromosomes required to accomplish a given control task. This new strategy is applied to the end-point tracking of a single-link flexible manipulator modelled from experimental data. Results show that the MNN controller is simple to design and produces superior performance compared to a single neural network (SNN) controller which is theoretically capable of achieving the desired trajectory. (C) 2003 Elsevier Ltd. All rights reserved.