This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: What is perceptual learning?

The purpose of this chapter is to outline some of the thinking behind new e-learning technology, including e-portfolios and personal learning environments. Part of this thinking is centered around the theory of connectivism, which asserts that knowledge - and therefore the learning of knowledge - is distributive, that is, not located in any given place (and therefore not 'transferred' or 'transacted' per se) but rather consists of the network of connections formed from experience and interactions with a (...) knowing community. And another part of this thinking is centered around the new, and the newly empowered, learner, the member of the net generation, who is thinking and interacting in new ways. These trends combine to form what is sometimes called 'e-learning 2.0' - an approach to learning that is based on conversation and interaction, on sharing, creation and participation, on learning not as a separate activity, but rather, as embedded in meaningful activities such as games or workflows. (shrink)

Considerable interest has been shown in models of inter-organisational collaboration including clusters, networks and recently supply chains. Arguably effective configurations of enterprises can work together to achieve some form of what is termed ‘collective efficiency’ which enables them to cope with the challenges of the current competitive encironment. This paper addresses one aspect of such collective efficiency: the potential acceleration and improvement of the process of knowledge acquisition and capacity building through shared learning. It explores the concept of (...) formal ‘learning networks’ and reports on UK research into the design and operation of such networks. (shrink)

With the growth of neuroscience research, new neuroscience and society (NeuroX) fields like neuroethics, neurolaw, neuroarchitecture, neuroeconomics, and many more have emerged. In this article we report on lessons learned about mentoring students in the interdisciplinary space of neuroscience and society. We draw on our experiences with the recently launched Dana Foundation Career Network in Neuroscience & Society. This resource supports educators and practitioners mentoring students aiming to apply neuroscience in diverse fields beyond medicine and biomedical science. Through our programming, (...) we identified three key lessons: (1) students are interested in exploring a wide range of neuroscience and society intersections; (2) outreach to underserved institutions generates avenues for students to join NeuroX conversations; and (3) by offering free access to online NeuroX resources and a network of subject-matter experts, the Career Network joins many partners helping to bridge the gap between neuroscience and society. (shrink)

With the rapid development of artificial intelligence technology, multitasking textual translation has attracted more and more attention. Especially after the application of deep learning technology, the performance of multitask translation text detection and recognition has been greatly improved. However, because multitasking contains the interference problem faced by the translated text, there is a big gap between recognition performance and actual application requirements. Aiming at multitasking and translation text detection, this paper proposes a text localization method based on multichannel multiscale (...) detection of the largest stable extreme value region and cascade filtering. This paper selects the appropriate color channel and scale to extract the maximum stable extreme value area as the character candidate area and designs a cascaded filter from coarse to fine to remove false detections. The coarse filter is based on some simple morphological features and stroke width features, and the fine filter is trained by a two-recognition convolutional neural network. The remaining character candidate regions are merged into horizontal or multidirectional character strings through the graph model. The experimental results on the text data set prove the effectiveness of the improved deep learning network character model and the feasibility of the textual implication translation analysis method based on this model. Among them, the text contains translation character recognition results prove that the model has good description ability. The characteristics of the model determine that this method is not sensitive to the scale of the sliding window, so it performs better than the existing typical methods in retrieval tasks. (shrink)

Legal Judgment Prediction (LJP) is a typical application of Artificial Intelligence in the intelligent judiciary. Current research primarily focuses on automatically predicting law articles, charges, and terms of penalty based on the fact description of cases. However, existing methods for LJP have limitations, such as neglecting document structure and ignoring case similarities. We propose a novel framework called Graph Contrastive Learning with Augmentation (GCLA) for legal judgment prediction to address these issues. GCLA constructs trainable document-level graphs for fact description, (...) capturing local and global context through sentence-level subgraphs. Graph augmentation enhances robustness. We introduce a comparison case relation perspective, using graph contrastive learning to model case-text label relationships effectively. Experimental results on real-world datasets demonstrate the competitive performance of GCLA. (shrink)

Do properties of a word's features influence the order of its acquisition in early word learning? Combining the principles of mutual exclusivity and shape bias, the present work takes a network analysis approach to understanding how feature distinctiveness predicts the order of early word learning. Distance networks were built from nouns with edge lengths computed using various distance measures. Feature distinctiveness was computed as a distance measure, showing how far an object in a network is from other (...) objects based on shared and non-shared features. Feature distinctiveness predicted order of acquisition across all measures: Words that were further away from other words in the network space were learned earlier. The best distance measures were based only on non-shared features and did not include shared features. This indicates that shared features may play less of a role in early word learning than non-shared features. In addition, the strongest effects were found for visual form and surface features. Cluster analysis further revealed that this effect is a localized effect in the object feature space, where objects' distances from their cluster centroid were inversely correlated with their age of acquisition. Together, these results suggest a role for feature distinctiveness in early word learning. (shrink)

Intelligent Tutoring Systems (ITS) has a wide influence on the exchange rate, education, health, training, and educational programs. In this paper we describe an intelligent tutoring system that helps student study computer networks. The current ITS provides intelligent presentation of educational content appropriate for students, such as the degree of knowledge, the desired level of detail, assessment, student level, and familiarity with the subject. Our Intelligent tutoring system was developed using ITSB authoring tool for building ITS. A preliminary evaluation (...) of the ITS was done by a group of students and teachers. The results were acceptable. (shrink)

Organizational cybernetics offers theoretical and methodological support for self-organizing communities seeking to contribute to the conscious evolution of society. Previous experiences with the Viable Systems Model (VSM) and Team Syntegrity (TS) illustrate ways of enabling social networks to create a shared language, reach democratic agreements, and develop knowledge networks.

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine, a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can (...) encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models. We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. (shrink)

In this chapter, I consider three ‘promises’ of bringing phenomenology into dialogue with networked learning. First, a ‘conceptual promise’, which draws attention to conceptual resources in phenomenology that can inspire and inform how we understand, conceive of, and uncover experiences of participants in networked learning activities and environments. Second, a ‘methodological promise’, which outlines a variety of ways that phenomenological methodologies and concepts can be put to use in empirical research in networked learning. And third, a ‘critical (...) promise’, which suggests how work done in the realm of critical phenomenology is complementary to and useful for exploring the social justice and emancipatory aims of networked learning researchers. Through this framework, I reflect upon multiple ways in which phenomenology has and might continue to fruitfully inform and shape networked learning research. In doing so, I emphasise that deploying phenomenology in the context of networked learning not only enriches our understanding of networked learning but that phenomenology itself is enriched through testing, finetuning, and expanding its methods, concepts, and understanding, as well as unveiling its own limitations and constraints. (shrink)

From an analysis of the role of companies in multi-stakeholder networks and a critical review of stakeholder theory, it is argued that companies practise two different types of stakeholder management: they focus on their organization’s welfare (organization- focussed stakeholder management) or on an issue that affects their relationship with other societal groups and organizations (issue-focussed stakeholder management). These two approaches supplement each other. It is demonstrated that issue-focussed stakeholder management dominates in multi-stakeholder networks, because it enables corporations to (...) address complex problems and challenges in cooperation with stakeholders. Since deliberation is the key to issue-focussed stakeholder management, it helps to cope with numerous and at times contradictory stakeholder demands and enhances the legitimacy of corporate activities. (shrink)

A sector is a basic unit of airspace whose operation is managed by air traffic controllers. The operation complexity of a sector plays an important role in air traffic management system, such as airspace reconfiguration, air traffic flow management, and allocation of air traffic controller resources. Therefore, accurate evaluation of the sector operation complexity is crucial. Considering there are numerous factors that can influence SOC, researchers have proposed several machine learning methods recently to evaluate SOC by mining the relationship (...) between factors and complexity. However, existing studies rely on hand-crafted factors, which are computationally difficult, specialized background required, and may limit the evaluation performance of the model. To overcome these problems, this paper for the first time proposes an end-to-end SOC learning framework based on deep convolutional neural network specifically for free of hand-crafted factors environment. A new data representation, i.e., multichannel traffic scenario image, is proposed to represent the overall air traffic scenario. A MTSI is generated by splitting the airspace into a two-dimension grid map and filled with navigation information. Motivated by the applications of deep learning network, the specific CNN model is introduced to automatically extract high-level traffic features from MTSIs and learn the SOC pattern. Thus, the model input is determined by combining multiple image channels composed of air traffic information, which are used to describe the traffic scenario. The model output is SOC levels for the target sector. The experimental results using a real dataset from the Guangzhou airspace sector in China show that our model can effectively extract traffic complexity information from MTSIs and achieve promising performance than traditional machine learning methods. In practice, our work can be flexibly and conveniently applied to SOC evaluation without the additional calculation of hand-crafted factors. (shrink)

The Internet of Things (IoT) is a fast-growing technology that connects everyday devices to the Internet, enabling wireless, low-consumption and low-cost communication and data exchange. IoT has revolutionized the way devices interact with each other and the internet. The more devices become connected, the greater the risk of security breaches. There is currently a need for new approaches to algorithms that can detect malware regardless of the size of the network and that can adapt to dynamic changes in the network. (...) Through the use of a multi-agent reinforcement learning algorithm, this paper proposes a novel algorithm for malware detection in IoT devices. The proposed algorithm is not strongly dependent on the size of the IoT network due to the that its training is adapted using time differences if the IoT network size is small or Monte Carlo otherwise. To validate the proposed algorithm in an environment as close to reality as possible, we proposed a scenario based on a real IoT network, where we tested different malware propagation models. Different simulations varying the number of agents and nodes in the IoT network have been developed. The result of these simulations proves the efficiency and adaptability of the proposed algorithm in detecting malware, regardless of the malware propagation model. (shrink)

We investigate a simple stochastic model of social network formation by the process of reinforcement learning with discounting of the past. In the limit, for any value of the discounting parameter, small, stable cliques are formed. However, the time it takes to reach the limiting state in which cliques have formed is very sensitive to the discounting parameter. Depending on this value, the limiting result may or may not be a good predictor for realistic observation times.

Can neural networks be applied in voting theory, while satisfying the need for transparency in collective decisions? We propose axiomatic deep voting: a framework to build and evaluate neural networks that aggregate preferences, using the well-established axiomatic method of voting theory. Our findings are: (1) Neural networks, despite being highly accurate, often fail to align with the core axioms of voting rules, revealing a disconnect between mimicking outcomes and reasoning. (2) Training with axiom-specific data does not enhance (...) alignment with those axioms. (3) By solely optimizing axiom satisfaction, neural networks can synthesize new voting rules that often surpass and substantially differ from existing ones. This offers insights for both fields: For AI, important concepts like bias and value-alignment are studied in a mathematically rigorous way; for voting theory, new areas of the space of voting rules are explored. (shrink)

This paper considers how surprise (or its lack) can be cast as a metacognitive signal with an adaptive function in learning new knowledge and revising belief networks. It reviews the phenomena that may hinder this signal (e.g., hindsight bias) and argues for its extrinsic exploitation in instructional and educational contexts by educators, journalists and parents, who might train learners to internalize the use of surprise to drive explanation‐based learning.

This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: Can perceptual experience be modified by reason?

This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How does perceptual learning alter the contents of perception?

This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How is perceptual learning coordinated with action?

This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How does perceptual learning alter perceptual phenomenology?

Meta-learning is even more broadly relevant to the study of inductive biases than Binz et al. suggest: Its implications go beyond the extensions to rational analysis that they discuss. One noteworthy example is that meta-learning can act as a bridge between the vector representations of neural networks and the symbolic hypothesis spaces used in many Bayesian models.

This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: How should we demarcate perceptual learning from perceptual development?

Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models (...) of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explore systematically the complex interaction between learning and representation, as we try to demonstrate through the analysis of several large networks. (shrink)

This is an overview work on adaptive social networks. Individuals interact with neighbors on a random network. The evolution of the (probabilistic) network structure is driven by reinforcement learning. The strategies of players co-evolve with the network structure. Rapidly evolving network structure favors cooperation.

When making decisions, humans can observe many kinds of information about others' activities, but their effects on performance are not well understood. We investigated social learning strategies using a simple problem-solving task in which participants search a complex space, and each can view and imitate others' solutions. Results showed that participants combined multiple sources of information to guide learning, including payoffs of peers' solutions, popularity of solution elements among peers, similarity of peers' solutions to their own, and relative (...) payoffs from individual exploration. Furthermore, performance was positively associated with imitation rates at both the individual and group levels. When peers' payoffs were hidden, popularity and similarity biases reversed, participants searched more broadly and randomly, and both quality and equity of exploration suffered. We conclude that when peers' solutions can be effectively compared, imitation does not simply permit scrounging, but it can also facilitate propagation of good solutions for further cumulative exploration. (shrink)

__Learning for Careers_ provides a comprehensive account of the Pathways to Prosperity Network, a national initiative focused on helping more young people successfully complete high school, attain a first postsecondary credential with value in the labor market, and get started on a career without foreclosing the opportunity for further education._ It takes as its starting point the influential 2011 _Pathways to Prosperity_ report, which challenged the prevailing idea that the core mission of high schools was to prepare all students for (...) college. In response, the Pathways Network was founded in 2012 to promote cooperative arrangements between educational and business institutions in order to fashion pathways for young people to acquire twenty-first-century skills and achieve professional success. This book traces the evolution of the Pathways Network over the past five years, focusing on the efforts of a diverse set of states and regions to build systems that span high school and the first two years of postsecondary education. States such as Delaware and Tennessee have been highly effective in establishing systems designed to equip students with credentials valued in the contemporary labor market. At the same time, the authors acknowledge the technical, political, and cultural challenges in redesigning career-focused education to produce satisfactory outcomes for young people throughout the country. _Learning for Careers_ offers a way forward for the millions of young people and employers that face a rapidly evolving and ever more competitive globalized workplace. This book will be essential reading for all who have a stake in educational and economic opportunity in the United States. (shrink)

In this article we present symmetric diffusion networks, a family of networks that instantiate the principles of continuous, stochastic, adaptive and interactive propagation of information. Using methods of Markovion diffusion theory, we formalize the activation dynamics of these networks and then show that they can be trained to reproduce entire multivariate probability distributions on their outputs using the contrastive Hebbion learning rule (CHL). We show that CHL performs gradient descent on an error function that captures differences (...) between desired and obtained continuous multivariate probability distributions. This allows the learning algorithm to go beyond expected values of output units and to approximate complete probability distributions on continuous multivariate activation spaces. We argue that learning continuous distributions is an important task underlying a variety of real‐life situations that were beyond the scope of previous connectionist networks. Deterministic networks, like back propagation, cannot learn this task because they are limited to learning average values of independent output units. Previous stochastic connectionist networks could learn probability distributions but they were limited to discrete variables. Simulations show that symmetric diffusion networks can be trained with the CHL rule to approximate discrete and continuous probability distributions of various types. (shrink)

Phishing attacks are a significant issue in cybersecurity, and extensive efforts with machine learning methods have been made to detect them. The high similarity between benign and phishing URLs requires a substantial amount of data for effective training, but ever-changing attacks hinder us from preparing for sufficient data. To cope with the issue of limited data, this paper proposes a triplet-sampled prototypical network, which learns the characteristics of URL samples for various phishing classes with appropriate prototypes trained with contrastive (...) learning. For a new input URL, the learned model finds the most similar prototypes contrasted by themselves and calculates the average distance to judge whether it is phishing or not. Experiments with the three benchmark datasets of ISCX-URL-2016, PhishStorm, and PhishTank show an impressive performance of 99.83%, 98.61%, and 97.79%, respectively. Additional experiment with 100-, 10-, 5-, and 1-shot scenarios demonstrates that the proposed method allows for efficient and effective detection of phishing URLs even with a limited number of training data. (shrink)

To speak of “networked learning” (e.g., NLEC, 2021a) is to subsume a wide range of educational questions under two overdetermined rubrics. “Learning” and “networked” are words that already carry a heavy semantic burden in both educational and technological discourses. First, the word “learning”—as used in networked learning and in educational discourse generally—tends to conflate the roles and responsibilities of student and teacher. Second, and again as in educational discourse broadly, the definitions provided for networked learning (...) fail to clearly distinguish between “is” and “ought,” between description and prescription. The task of carefully defining networked learning is justified as providing “a concise description of a field of research and practice” but relies on normative criteria that have no unambiguous descriptive corollaries. Third and finally, to speak of experiences as “networked” is to direct attention to structured, interconnected, or entangled manifestations of learning. This is incompatible with the ontological presuppositions of phenomenology and with phenomenological accounts of learning as “non-disponible:” inaccessible, non-available, and non-controllable. (shrink)

The shift in corporate strategy, from vertical integration to strategic alliances, has developed hand in hand with the evolution of organizational structure, from the vertically integrated firm to the network organization. The result has been the elimination of boundaries, more flexible organizations, and a greater interaction among individuals and organizations. On the negative side, the specialization of firms on single areas of competence has resulted in the disaggregation of the value chain and in the disaggregation of ethical and legal responsibility. (...) To illustrate this point, the paper considers some cases, such as the case of the "beer girls" of Southeast Asia, who are used unethically by distributors to sell beer and liquor. To deal with the problem of the disaggregation of ethical responsibility, managers can use organizational culture and ethical values to control the performance of employees and of other organizations. Contemporary developments in business ethics also offer tools for dealing with the problem. For example, "global corporate citizenship," integrated social contracting theory, and stakeholder learning dialogues provide ways of integrating the interests of all stakeholders. The task is now to use these new approaches to create a governance process that incorporates the voices of all stakeholders, especially the voices of those stakeholders that have legitimate and urgent moral claims, but lack the power to establish those claims. (shrink)

Sibley et al. (2008) report a recurrent neural network model designed to learn wordform representations suitable for written and spoken word identification. The authors claim that their sequence encoder network overcomes a key limitation associated with models that code letters by position (e.g., CAT might be coded as C‐in‐position‐1, A‐in‐position‐2, T‐in‐position‐3). The problem with coding letters by position (slot‐coding) is that it is difficult to generalize knowledge across positions; for example, the overlap between CAT and TOMCAT is lost. Although we (...) agree this is a critical problem with many slot‐coding schemes, we question whether the sequence encoder model addresses this limitation, and we highlight another deficiency of the model. We conclude that alternative theories are more promising. (shrink)

The traditional organizational boundaries between healthcare, social work, police and other non-profit organizations are fading and being replaced by new relational patterns among a variety of disciplines. Professionals work from their own history, role, values and relationships. It is often unclear who is responsible for what because this new network structure requires rules and procedures to be re-interpreted and re-negotiated. A new moral climate needs to be developed, particularly in the early stages of integrated services. Who should do what, with (...) whom and why? Departing from a relational and hermeneutic perspective, this article shows that professionals in integrated service networks embark upon a moral learning process when starting to work together for the client’s benefit. In this context, instrumental ways of thinking about responsibilities are actually counterproductive. Instead, professionals need to find out who they are in relation to other professionals, what core values they share and what responsibilities derive from these aspects. This article demonstrates moral learning by examining the case of an integrated social service network. The network’s development and implementation were supported by responsive evaluation, enriched by insights of care ethics and hermeneutic ethics. (shrink)

This chapter investigates a simple stochastic model of social network formation by the process of reinforcement learning with discounting of the past. In the limit, for any value of the discounting parameter, small, stable cliques are formed. However, the time it takes to reach the limiting state in which cliques have formed is very sensitive to the discounting parameter. Depending on this value, the limiting result may or may not be a good predictor for realistic observation times.

With the rapid growth of informatics systems’ technology in this modern age, the Internet of Things (IoT) has become more valuable and vital to everyday life in many ways. IoT applications are now more popular than they used to be due to the availability of many gadgets that work as IoT enablers, including smartwatches, smartphones, security cameras, and smart sensors. However, the insecure nature of IoT devices has led to several difficulties, one of which is distributed denial-of-service (DDoS) attacks. IoT (...) systems have several security limitations due to their disreputability characteristics, like dynamic communication between IoT devices. The dynamic communications resulted from the limited resources of these devices, such as their data storage and processing units. Recently, many attempts have been made to develop intelligent models to protect IoT networks against DDoS attacks. The main ongoing research issue is developing a model capable of protecting the network from DDoS attacks that is sensitive to various classes of DDoS and can recognize legitimate traffic to avoid false alarms. Subsequently, this study proposes combining three deep learning algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM)-RNN, and convolutional neural network (CNN), to build a bidirectional CNN-BiLSTM DDoS detection model. The RNN, CNN, LSTM, and CNN-BiLSTM are implemented and tested to determine the most effective model against DDoS attacks that can accurately detect and distinguish DDoS from legitimate traffic. The intrusion detection evaluation dataset (CICIDS2017) is used to provide more realistic detection. The CICIDS2017 dataset includes benign and up-to-date examples of typical attacks, closely matching real-world data of Packet Capture. The four models are tested and assessed using Confusion Metrix against four commonly used criteria: accuracy, precision, recall, and F-measure. The performance of the models is quite effective as they obtain an accuracy rate of around 99.00%, except for the CNN model, which achieves an accuracy of 98.82%. The CNN-BiLSTM achieves the best accuracy of 99.76% and precision of 98.90%. (shrink)

Current challenges to sustaining public support for health data research have directed attention to the governance of data-intensive health research networks. Accountability is hailed as an important element of trustworthy governance frameworks for data-intensive health research networks. Yet the extent to which adequate accountability regimes in data-intensive health research networks are currently realized is questionable. Current governance of data-intensive health research networks is dominated by the limitations of a drawing board approach. As a way forward, we (...) propose a stronger focus on accountability as learning to achieve accountable governance. As an important step in that direction, we provide two pathways: (1) developing an integrated structure for decision-making and (2) establishing a dialogue in ongoing deliberative processes. Suitable places for learning accountability to thrive are dedicated governing bodies as well as specialized committees, panels or boards which bear and guide the development of governance in data-intensive health research networks. A continuous accountability process which comprises learning and interaction accommodates the diversity of expectations, responsibilities and tasks in data-intensive health research networks to achieve responsible and effective governance. (shrink)

The area of smart power grids needs to constantly improve its efficiency and resilience, to provide high quality electrical power in a resilient grid, while managing faults and avoiding failures. Achieving this requires high component reliability, adequate maintenance, and a studied failure occurrence. Correct system operation involves those activities and novel methodologies to detect, classify, and isolate faults and failures and model and simulate processes with predictive algorithms and analytics. In this paper, we showcase the application of a complex-adaptive, self-organizing (...) modeling method, and Probabilistic Boolean Networks, as a way towards the understanding of the dynamics of smart grid devices, and to model and characterize their behavior. This work demonstrates that PBNs are equivalent to the standard Reinforcement Learning Cycle, in which the agent/model has an interaction with its environment and receives feedback from it in the form of a reward signal. Different reward structures were created to characterize preferred behavior. This information can be used to guide the PBN to avoid fault conditions and failures. (shrink)

Nowadays, the development of human society and daily life are inseparable from the power supply. Therefore, people also put forward higher requirements for the reliability of distribution network, but power companies can only passively deal with distribution network failures, which is a bottleneck for the improvement of distribution network reliability. The Internet of Things is the best solution for online equipment status monitoring and basic data sharing for large, widely distributed, relatively fixed, and large numbers of equipment. The construction of (...) the IoT for power distribution equipment faces many important problems, including the selection of networking, equipment selection, and interaction standards. When researching the implementation plan, research on the distribution of IoT market was carried out. Based on the grid, the idea of optimizing the investment selection plan of the power distribution using IoT was discussed, and a result verification model was established. After the completion of the theoretical part, a case study of medium-voltage distribution grid equipment management and medium-voltage distribution network equipment management based on the grid was carried out by taking a real enterprise application situation as an example. Realizing fault diagnosis of distribution network will not only provide decision support for operation and maintenance of distribution network for power companies, but also have great economic and social benefits. Aiming at the shortcomings of single data mining method in distribution network fault diagnosis, hybrid data mining method is proposed. First, rough set theory is used to reduce the original fault data and form a simplified rule set. Because of the non-linearity of distribution network fault and the strong learning ability, adaptability, and robustness of Bayesian network, Bayesian network can be used to classify distribution network faults. Therefore, a simplified fault diagnosis system is established in this paper, and its correctness is confirmed. Then, the learning and training are carried out by using Bayesian network to call the simplest rule set, which has the characteristics of short learning and training time and high diagnostic accuracy. (shrink)

One of the most challenging tasks when adopting Bayesian networks is the one of learning their structure from data. This task is complicated by the huge search space of possible solutions and by the fact that the problem isNP-hard. Hence, a full enumeration of all the possible solutions is not always feasible and approximations are often required. However, to the best of our knowledge, a quantitative analysis of the performance and characteristics of the different heuristics to solve this (...) problem has never been done before. For this reason, in this work, we provide a detailed comparison of many different state-of-the-art methods for structural learning on simulated data considering both BNs with discrete and continuous variables and with different rates of noise in the data. In particular, we investigate the performance of different widespread scores and algorithmic approaches proposed for the inference and the statistical pitfalls within them. (shrink)

The present commentary addresses the Quartz & Sejnowski (Q&S) target article from the point of view of the dynamical learning algorithm for neural networks. These techniques implicitly adopt Q&S's neural constructivist paradigm. Their approach hence receives support from the biological and psychological evidence. Limitations of constructive learning for neural networks are discussed with an emphasis on grammar learning.

A central challenge for research on how we should prepare students to manage crossing boundaries between different knowledge settings in life long learning processes is to identify those forms of knowledge that are particularly relevant here. In this paper, we develop by philosophical means the concept of a dialectical system as a general framework to describe the de-velopment of knowledge networks that mark the starting point for learning processes, and we use semiotics to discuss the epistemological thesis (...) that any cognitive access to our world of objects is mediated by signs and diagrammatic reasoning and abduction as those forms of practical knowledge that are crucial for the development of knowledge networks. The rich-ness of this theoretical approach becomes evident by applying it to an example of learning in a biological research context. At the same time, we take a new look at the role of mathematical knowledge in this process. (shrink)

A new multi-disciplinary degree program in education and information studies was developed to uniquely facilitate educators’ capacity to be responsive to the demands of a digitally connected world. Charles Sturt University’s Master of Education (Knowledge Networks and Digital Innovation) aims to develop agile leaders in new cultures of digital formal and informal learning. The co-construction of knowledge through interpersonal discourse creates a pedagogical tension between a focus on knowledge-based instruction and outcomes, and on praxis-based instruction. This digital context (...) draws attention to academic integrity issues in online learning environments. Through the new subject Game-Based Learning, students engaged in theory, practice, trends in game designs and immersive aspects of game, utilizing the technology and pedagogical affordances of a range of online tools. The subject builds on the keystone subject and incorporates reflective participation and a culture of participatory learning through integration of social media, social scholarship and open sharing of ideas, resources and experiences online within the broader education community. Subject engagement and assessment design incorporated academic integrity strategies, and needed individual and group collaboration to be fully integrated into the learning experience of the students, thus modeling practices relevant to the student’s own processional practices. This paper also considers the contribution of global connectedness to the success of the pedagogic processes used for embedding academic integrity through social scholarship into the curriculum and learning experiences. (shrink)

The contribution that may come from the general science of signs, semiotics, to the planning and development of education and learning at all levels, from early schooling through to university education and learning should not be neglected. As Umberto Eco claims in the “Introduction” to the Italian edition of his book Semiotica and Philosophy of Language (1984: xii, my trans.), “[general semiotics] is philosophical in nature, because it does not study a particular system, but posits the general categories (...) in light of which different systems can be compared. And for general semiotics philosophical discourse is neither advisable nor urgent: it is simply constitutive.” To the title of their book Semiotic Theory of Learning, at the centre of our attention in the present text, Andrew Stables, Winfried Nöth, Alin Olteanu, Sébastien Pesce, and Eetu Pikkarainen, rightly add the subtitle New Perspectives in the Philosophy of Education. This multivoiced contribution to research in learning and education in a semiotic framework has a unifying reference in the semiotics of Charles S. Peirce, but without disregarding an array of other distinguished exponents of the teaching and education sciences from different disciplines, semioticians and philosophers alike. This book, a polyphonic effort, with its appeal to “act otherwise,” and to do so investing in learning and education, no doubt makes a significant contribution in such a direction: education for transformation, for humanizing social change. Beyond evidencing what to us are particularly interesting aspects of the topics under discussion in Semiotic Theory of Learning, we also propose to continue and amplify this multivoiced dialogue. While highlighting still other aspects and contributions made by the same semioticians and philosophers presented by the authors of this book, involving such figures as Charles Peirce, Charles Morris, Thomas Sebeok, John Deely, etc., we have further introduced other voices made to resound throughout, whether directly or indirectly, like that of Victoria Welby, Mikhail Bakhtin, Emmanuel Levinas, Adam Schaff, Ferruccio Rossi-Landi, Marcel Danesi, Augusto Ponzio, and Genevieve Vaughan. (shrink)

In species capable of learning, including our own, individuals can modify their behavior by some adaptive process. Important classes of behavior - mating, predation, coalitions, trade, signaling, and division of labor - involve interactions between individuals. The agents involved learn two things: with whom to interact and how to act. That is to say that adaptive dynamics operates both on structure and strategy.

Learning, which is the main key of innovation, is an indispensable element for companies to gain sustainable competitive advantage. Although not being adequately studied in management literature, network learning capability, a type of organizational learning ability, is a determining factor in the innovation process. Likewise, open-mindedness is a component that accelerates the creation of knowledge in the organization as well as encouraging the organization to be open towards new opportunities and to value different opinions. In this study, (...) a model including these variables was designed and the mediator role of network learning in the relationship between open-mindedness and innovation performance was explored. It is suggested that open-mindedness has a positive effect on innovation performance and that network learning capability possesses a mediator role in this relationship. The data were collected through surveys answered by the middle and senior managers of Turkey’s leading companies. As a result, it is pointed out that there is a positive and significant relationship between open-mindedness and innovation performance, and that network learning has a mediator effect on this relationship. This study adds value to the management literature by highlighting the momentousness of network learning capability in the innovation process as well as offering several avenues of future studies and implications for different stakeholders. (shrink)