Search

Due to tremendous progress in digital electronics now intelligent and autonomous agents are gradually being adopted into the fields and domains of the military, defense and warfare. This paper tries to explore some of the inherent ethical issues, threats and some remedial issues about the impact of such systems on human civilization and existence in general. This paper discusses human ethics in contrast to machine ethics and the problems caused by non-sentient agents. A systematic study is made on paradoxes regarding the long-term advantages of such agents in military combat. This paper proposes an international standard which could be adopted by all nations to bypass the adverse effects and solve ethical issues of such intelligent agents.

As a human product, language reflects the psychological experience of man (Radden and Dirven, 2007). One model of language and human cognition in general is connectionism, by many linguists is regarded as mathematical and, therefore, too reductive. This opinion trend seems to be reversing, however, due to the fact that many cognitive researchers begin to appreciate one attribute of network models: feature emergence. In the course of a network simulation properties emerge that were neither inbuilt nor intended by its creators (Elman, 1998), in other words, the whole becomes more than just the sum of its parts. Insight is not only drawn from the network's output, but also the means that the network utilizes to arrive at the output. It may seem obvious that the events of life should be meaningful for human beings, yet there is no widely accepted theory as to how do we derive that meaning. The most promising hypothesis regarding the question how the world is meaningful to us is that of embodied cognition (cf. Turner 2009), which postulates that the functions of the brain evolved so as to ‘understand’ the body, thus grounding the mind in an experiential foundation. Yet, the relationship between the body and the mind is far from perspicuous, as research insight is still intertwined with metaphors specific for the researcher’s methodology (Eliasmith 2003). It is the aim of this paper to investigate the conceptual metaphor in a manner that will provide some insight with regard to the role that objectification, as defined by Szwedek (2002), plays in human cognition and identify one possible consequence of embodied cognition. If the mechanism for concept formation, or categorization of the world, resembles a network, it is reasonable to assume that evidence for this is to be sought in language. Let us then postulate the existence of a network mechanism for categorization and concept formation present in the human mind and initially developed to cope with the world directly accessible to the early human (i.e. tangible). Such a network would convert external inputs to form an internal, multi modal representation of a perceived object in the brain. The sheer amount of available information and the computational restrictions of the brain would force some sort of data compression, or a computational funnel. It has been shown that a visual perception network of this kind can learn to accurately label patterns (Elman, 1998). What is more, the compression of data facilitated the recognition of prototypes of a given pattern category rather than its peripheral representations, an emergent property that supports the prototype theory of the mental lexicon (cf. Radden and Dirven, 2007). The present project proposes that, in the domain of cognition, the process of objectification, as defined by Szwedek (2002), would be an emergent property of such a system, or that if an abstract notion is computed by a neural network designed to cope with tangible concepts the data compression mechanism would require the notion to be conceptualized as an object to permit further processing. The notion of emergence of meaning from the operation of complex systems is recognised as an important process in a number of studies on metaphor comprehension. Feature emergence is said to occur when a non-salient feature of the target and the vehicle becomes highly salient in the metaphor (Utsumi 2005). Therefore, for example, should objectification emerge as a feature in the metaphor KNOWLEDGE IS A TREASURE, the metaphor would be characterised as having more features of an object than either the target or vehicle alone. This paper focuses on providing a theoretical connectionist network based on the Elman-type network (Elman, 1998) as a model of concept formation where objectification would be an emergent feature. This is followed by a psychological experiment whereby the validity of this assumption is tested through a questionnaire where two groups of participants are asked to evaluate either metaphors or their components. The model proposes an underlying relation between the mechanism for concept formation and the omnipresence of conceptual metaphors, which are interpreted as resulting from the properties of the proposed network system. Thus, an evolutionary neural mechanism is proposed for categorization of the world, that is able to cope with both concrete and abstract notions and the by-product of which are the abstract language-related phenomena, i.e. metaphors. The model presented in this paper aims at providing a unified account of how the various types of phenomena, objects, feelings etc. are categorized in the human mind, drawing on evidence from language. References: Szwedek, Aleksander. 2002. Objectification: From Object Perception To Metaphor Creation. In B. Lewandowska-Tomaszczyk and K. Turewicz (eds). Cognitive Linguistics To-day, 159-175. Frankfurt am Main: Peter Lang. Radden, Günter and Dirven, René. 2007. Cognitive English Grammar. Amsterdam/ Philadelphia: John Benjamins Publishing Company Eliasmith, Chris. 2003. Moving beyond metaphors: understanding the mind for what it is. Journal of Philosophy. C(10):493- 520. Elman, J. L. et al. 1998. Rethinking innateness: A connectionist perspective on development. Cambridge, MA: MIT Press Turner, Mark. 2009. Categorization of Time and Space Through Language. (Paper presented at the FOCUS2009 conference "Categorization of the world through language". Serock, 25-28 February 2009). Utsumi, Akira. 2005. The role of feature emergence in metaphor appreciation, Metaphor and Symbol, 20(3), 151-172.

In this paper, we explore the interplay between network topology and time criticality in a military logistics system. A general goal of this work (and previous work) is to evaluate land transportation requirements or, more specifically, how to design appropriate fleets of military general service vehicles that are tasked with the supply and re-supply of military units dispersed in an area of operation. The particular focus of this paper is to gain a better understanding of how the logistics environment changes when current Army vehicles with fixed transport characteristics are replaced by a new generation of modularised vehicles that can be configured task-specifically. The experimental work is conducted within a well developed strategic planning simulation environment which includes a scenario generation engine for automatically sampling supply and re-supply missions and a multi-objective meta-heuristic search algorithm (i.e. Evolutionary Algorithm) for solving the particular scheduling and routing problems. The results presented in this paper allow for a better understanding of how (and under what conditions) a modularised vehicle fleet can provide advantages over the currently implemented system.

This paper introduces Latent Relational Analysis (LRA), a method for measuring semantic similarity. LRA measures similarity in the semantic relations between two pairs of words. When two pairs have a high degree of relational similarity, they are analogous. For example, the pair cat:meow is analogous to the pair dog:bark. There is evidence from cognitive science that relational similarity is fundamental to many cognitive and linguistic tasks (e.g., analogical reasoning). In the Vector Space Model (VSM) approach to measuring relational similarity, the similarity between two pairs is calculated by the cosine of the angle between the vectors that represent the two pairs. The elements in the vectors are based on the frequencies of manually constructed patterns in a large corpus. LRA extends the VSM approach in three ways: (1) patterns are derived automatically from the corpus, (2) Singular Value Decomposition is used to smooth the frequency data, and (3) synonyms are used to reformulate word pairs. This paper describes the LRA algorithm and experimentally compares LRA to VSM on two tasks, answering college-level multiple-choice word analogy questions and classifying semantic relations in noun-modifier expressions. LRA achieves state-of-the-art results, reaching human-level performance on the analogy questions and significantly exceeding VSM performance on both tasks.

We propose, in this paper, a teaching program based on a grammar of scientific language borrowed mostly from the area of knowledge representation in computer science and logic. The paper introduces an operationizable framework for understanding knowledge using knowledge representation (KR) methodology. We start with organizing concepts based on their cognitive function, followed by assigning valid and authentic semantic relations to the concepts. We propose that in science education, students can understand better if they organize their knowledge using the KR principles. The process, we claim, can help them to align their conceptual framework with that of experts which we assume is the goal of science education.

Qualitative models are more suitable than classical quantitative models in many tasks like Model-based Diagnosis (MBD), explaining system behavior, and designing novel devices from first principles. Monotonicity is an important feature to leverage when constructing qualitative models. Detecting monotone pieces robustly and efficiently from sensor or simulation data remains an open problem. This paper introduces an approach based on scale-dependent monotonicity: the notion that monotonicity can be defined relative to a scale. Real-valued functions defined on a finite set of reals e.g. the sensor data the simulation results, can be partitioned into quasi-monotone segments, i.e. segments monotone with respect to nonzero scale. We can identify the extrema of the quasi-monotone segments. This paper then uses this method to abstract qualitative models from simulation models for the purpose of diagnosis. It shows that using monotone analysis, the abstracted qualitative model is not only sound, but also parsimonious because it generates few landmarks.

What could a robot learn in one day? This paper describes the DayOne project, an endeavor to build an epigenetic robot that can bootstrap from a very rudimentary state to relatively sophisticated perception of objects and activities in a matter of hours. The project is inspired by the astonishingly rapidity with which many animals such as foals and lambs adapt to their surroundings on the first day of their life. While such plasticity may not be a sufficient basis for long-term cognitive development, it may be at least necessary, and share underlying infrastructure. This paper suggests that a sufficiently flexible perceptual system begins to look and act like it contains cognitive structures.

This paper summarizes the paper and poster contributions to the Third International Workshop on Epigenetic Robotics. The focus of this workshop is on the cross-disciplinary interaction of developmental psychology and robotics. Namely, the general goal in this area is to create robotic models of the psychological development of various behaviors. The term "epigenetic" is used in much the same sense as the term "developmental" and while we could call our topic "developmental robotics", developmental robotics can be seen as having a broader interdisciplinary emphasis. Our focus in this workshop is on the interaction of developmental psychology and robotics and we use the phrase "epigenetic robotics" to capture this focus.

This paper investigates how robots may emerge a lexicon to communicate complex meanings about actions such as `I am going to the red target' using simple (one-word) utterances. The main issue of the paper concerns the way these complex meanings represent the actions that are performed. It is argued that the meaning of these utterances may be represented without the need for categorising a complex flow of sensorimotor data. To illustrate the point, a simulation is presented in which robots develop such a communication system. The paper concludes by confirming that it is well possible to construct such a lexicon once robots have a number of basic sensorimotor skills available.

The field of language evolution and computation may benefit from using efficient and robust simulation tools that are based on widely exploited principles within the field. The tool presented in this paper is one that could fulfil such needs. The paper presents an overview of the tool -- THSim v3.2 -- and discusses some research questions that can be investigated with it.

An automatic choreography method to generate lifelike body movements is proposed. This method is based on somatics theories that are conventionally used to evaluate human’s psychological and developmental states by analyzing the body movement. The idea of this paper is to use the theories in the inverse way: to facilitate generation of artificial body movements that are plausible regarding evolutionary, developmental and emotional states of robots or other non-living movers. This paper reviews somatic theories and describes a strategy for implementations of automatic body movement generation. In addition, a psychological experiment is reported to verify expression ability on body movement rhythm. This method facilitates to choreographing body movement of humanoids, animal-shaped robots, and computer graphics characters in video games.

This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (thumbs down). The classification of a review is predicted by the average semantic orientation of the phrases in the review that contain adjectives or adverbs. A phrase has a positive semantic orientation when it has good associations (e.g., "subtle nuances") and a negative semantic orientation when it has bad associations (e.g., "very cavalier"). In this paper, the semantic orientation of a phrase is calculated as the mutual information between the given phrase and the word "excellent" minus the mutual information between the given phrase and the word "poor". A review is classified as recommended if the average semantic orientation of its phrases is positive. The algorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The accuracy ranges from 84% for automobile reviews to 66% for movie reviews.

Inductive concept learning is the task of learning to assign cases to a discrete set of classes. In real-world applications of concept learning, there are many different types of cost involved. The majority of the machine learning literature ignores all types of cost (unless accuracy is interpreted as a type of cost measure). A few papers have investigated the cost of misclassification errors. Very few papers have examined the many other types of cost. In this paper, we attempt to create a taxonomy of the different types of cost that are involved in inductive concept learning. This taxonomy may help to organize the literature on cost-sensitive learning. We hope that it will inspire researchers to investigate all types of cost in inductive concept learning in more depth.

This paper discusses some of the requirements for the control architecture of an intelligent human-like agent with multiple independent dynamically changing motives in a dynamically changing only partly predictable world. The architecture proposed includes a combination of reactive, deliberative and meta-management mechanisms along with one or more global ``alarm'' systems. The engineering design requirements are discussed in relation our evolutionary history, evidence of brain function and recent theories of Damasio and others about the relationships between intelligence and emotions. (The paper was completed in haste for a deadline and I forgot to explain why Descartes was in the title. See Damasio 1994.)

This position paper argues that in addition to the familiar approach using formal contexts, there is now a need in AI to study contexts as social constructs. As a successful example of the latter approach, I draw attention to `interpretation' (in the sense of literary theory), viz. the reconstruction of intended meaning of a literary text that takes into account the context in which the author assumed the reader would place the text. An important contribution here comes from Harris (1988), enumerating the seven crucial dimensions of context: knowledge of reality, knowledge of language, and the authorial, generic, collective, specific, and textual dimensions. Finally, two thought-provoking papers in interpretation, (Barwise 1989) and (Hobbs 1990), are analyzed as useful attempts which also come to grips with the notion of context.

A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi- dimensional feature space (also known as attribute-value descriptions). A teacher partitions a set of training examples into a finite number of classes. The task of the learning algorithm is to induce a concept from the training examples. In this paper, we formally distinguish three types of features: primary, contextual, and irrelevant features. We also formally define what it means for one feature to be context-sensitive to another feature. Context-sensitive features complicate the task of the learner and potentially impair the learner's performance. Our formal definitions make it possible for a learner to automatically identify context-sensitive features. After context-sensitive features have been identified, there are several strategies that the learner can employ for managing the features; however, a discussion of these strategies is outside of the scope of this paper. The formal definitions presented here correct a flaw in previously proposed definitions. We discuss the relationship between our work and a formal definition of relevance.

This is a philosophical `position paper', starting from the observation that we have an intuitive grasp of a family of related concepts of ``possibility'', ``causation'' and ``constraint'' which we often use in thinking about complex mechanisms, and perhaps also in perceptual processes, which according to Gibson are primarily concerned with detecting positive and negative affordances, such as support, obstruction, graspability, etc. We are able to talk about, think about, and perceive possibilities, such as possible shapes, possible pressures, possible motions, and also risks, opportunities and dangers. We can also think about constraints linking such possibilities. If such abilities are useful to us (and perhaps other animals) they may be equally useful to intelligent artefacts. All this bears on a collection of different more technical topics, including modal logic, constraint analysis, qualitative reasoning, naive physics, the analysis of functionality, and the modelling design processes. The paper suggests that our ability to use knowledge about ``de-re'' modality is more primitive than the ability to use ``de-dicto'' modalities, in which modal operators are applied to sentences. The paper explores these ideas, links them to notions of ``causation'' and ``machine'', suggests that they are applicable to virtual or abstract machines as well as physical machines. Some conclusions are drawn regarding the nature of mind and consciousness.

We have analyzed manufacturing data from several different semiconductor manufacturing plants, using decision tree induction software called Q-YIELD. The software generates rules for predicting when a given product should be rejected. The rules are intended to help the process engineers improve the yield of the product, by helping them to discover the causes of rejection. Experience with Q-YIELD has taught us the importance of data engineering -- preprocessing the data to enable or facilitate decision tree induction. This paper discusses some of the data engineering problems we have encountered with semiconductor manufacturing data. The paper deals with two broad classes of problems: engineering the features in a feature vector representation and engineering the definition of the target concept (the classes). Manufacturing process data present special problems for feature engineering, since the data have multiple levels of granularity (detail, resolution). Engineering the target concept is important, due to our focus on understanding the past, as opposed to the more common focus in machine learning on predicting the future.

This paper addresses the problem of classifying observations when features are context-sensitive, specifically when the testing set involves a context that is different from the training set. The paper begins with a precise definition of the problem, then general strategies are presented for enhancing the performance of classification algorithms on this type of problem. These strategies are tested on two domains. The first domain is the diagnosis of gas turbine engines. The problem is to diagnose a faulty engine in one context, such as warm weather, when the fault has previously been seen only in another context, such as cold weather. The second domain is speech recognition. The problem is to recognize words spoken by a new speaker, not represented in the training set. For both domains, exploiting context results in substantially more accurate classification.

This paper addresses the problem of classifying observations when features are context-sensitive, especially when the testing set involves a context that is different from the training set. The paper begins with a precise definition of the problem, then general strategies are presented for enhancing the performance of classification algorithms on this type of problem. These strategies are tested on three domains. The first domain is the diagnosis of gas turbine engines. The problem is to diagnose a faulty engine in one context, such as warm weather, when the fault has previously been seen only in another context, such as cold weather. The second domain is speech recognition. The context is given by the identity of the speaker. The problem is to recognize words spoken by a new speaker, not represented in the training set. The third domain is medical prognosis. The problem is to predict whether a patient with hepatitis will live or die. The context is the age of the patient. For all three domains, exploiting context results in substantially more accurate classification.

Based on formal-theoretical principles about the sign processes involved, we have built synthetic experiments to investigate the emergence of communication based on symbols and indexes in a distributed system of sign users, following theoretical constraints from C.S.Peirce theory of signs, following a Synthetic Semiotics approach. In this paper, we summarize these computational experiments and results regarding associative learning processes of symbolic sign modality and cognitive conditions in an evolutionary process for the emergence of either symbol-based or index-based communication.

Today, we can find many search engines which provide us with information which is more operational in nature. None of the search engines provide domain specific information. This becomes very troublesome to a novice user who wishes to have information in a particular domain. In this paper, we have developed an ontology which can be used by a domain specific search engine. We have developed an ontology on human anatomy, which captures information regarding cardiovascular system, digestive system, skeleton and nervous system. This information can be used by people working in medical and health care domain.

Gujarati is a resource poor language with almost no language processing tools being available. In this paper we have shown an implementation of a rule based stemmer of Gujarati. We have shown the creation of rules for stemming and the richness in morphology that Gujarati possesses. We have also evaluated our results by verifying it with a human expert.

Today, Plagiarism has become a menace. Every journal editor or conference organizers has to deal with this problem. Simply Copying or rephrasing of text without giving due credit to the original author has become more common. This is considered to be an Intellectual Property Theft. We are developing a Plagiarism Detection Tool which would deal with this problem. In this paper we discuss the common tools available to detect plagiarism and their short comings and the advantages of our tool over these tools.

Developing parallel corpora is an important and a difficult activity for Machine Translation. This requires manual annotation by Human Translators. Translating same text again is a useless activity. There are tools available to implement this for European Languages, but no such tool is available for Indian Languages. In this paper we present a tool for Indian Languages which not only provides automatic translations of the previously available translation but also provides multiple translations, in cases where a sentence has multiple translations, in ranked list of suggestive translations for a sentence. Moreover this tool also lets translators have global and local saving options of their work, so that they may share it with others, which further lightens the task.

Humans are cognitive entities. Our behaviors and ongoing interactions with the environment are threaded with creations and usages of meaningful information, be they conscious or unconscious. Animal life is also populated with meaningful information related to the survival of the individual and of the species. The meaningfulness of information managed by artificial agents can also be considered as a reality once we accept that the meanings managed by an artificial agent are derived from what we, the cognitive designers, have built the agent for. This rapid overview brings to consider that cognition, in terms of management of meaningful information, can be looked at as a reality for animal, humans and robots. But it is pretty clear that the corresponding meanings will be very different in nature and content. Free will and selfconsciousness are key drivers in the management of human meanings, but they do not exist for animals or robots. Also, staying alive is a constraint that we share with animals. Robots do not carry that constraint. Such differences in meaningful information and cognition for animal, humans and robots could bring us to believe that the analysis of cognitions for these three types of agents has to be done separately. But if we agree that humans are the result of the evolution of life and that robots are a product of human activities, we can then look at addressing the possibility for an evolutionary approach at cognition based on meaningful information management. A bottom-up path would begin by meaning management within basic living entities, then climb up the ladder of evolution up to us humans, and continue with artificial agents. This is what we propose to present here: address an evolutionary approach for cognition, based on meaning management using a simple systemic tool. We use for that an existing systemic approach on meaning generation where a system submitted to a constraint generates a meaningful information (a meaning) that will initiate an action in order to satisfy the constraint [1,2]. The action can be physical, mental or other. This systemic approach defines a Meaning Generator System (MGS). The simplicity of the MGS makes it available as a building block for meaning management in animals, humans and robots. Contrary to approaches on meaning generation in psychology or linguistics, the MGS approach is not based on human mind. To avoid circularity, an evolutionary approach has to be careful not to include components of human mind in the starting point. The MGS receives information from its environment and compares it with its constraint. The generated meaning is the connection existing between the received information and the constraint. The generated meaning is to trigger an action aimed at satisfying the constraint. The action will modify the environment, and so the generated meaning. Meaning generation links agents to their environments in a dynamic mode. The MGS approach is triadic, Peircean type. The systemic approach allows wide usage of the MGS: a system is a set of elements linked by a set of relations. Any system submitted to a constraint and capable of receiving information from its environment can lead to a MGS. Meaning generation can be applied to many cases, assuming we identify clearly enough the systems and the constraints. Animals, humans and robots are then agents containing MGSs. Similar MGSs carrying different constraints will generate different meanings. Cognition is system dependent. We first apply the MGS approach to animals with “stay alive” and “group life” constraints. Such constraints can bring to model many cases of meaning generation and actions in the organic world. However, it is to be highlighted that even if the functions and characteristics of life are well known, the nature of life is not really understood. Final causes are difficult to integrate in our today science. So analyzing meaning and cognition in living entities will have to take into account our limited understanding about the nature of life. Ongoing research on concepts like autopoiesis could bring a better understanding about the nature of life [3]. We next address meaning generation for humans. The case is the most difficult as the nature of human mind is a mystery for today science and philosophy. The natures of our feelings, free will or self-consciousness are unknown. Human constraints, meanings and cognition are difficult to define. Any usage of the MGS approach for humans will have to take into account the limitations that result from the unknown nature of human mind. We will however present some possible approaches to identify human constraints where the MGS brings some openings in an evolutionary approach [4, 5]. But it is clear that the better human mind will be understood, the more we will be in a position to address meaning management and cognition for humans. Ongoing research activities relative to the nature of human mind cover many scientific and philosophical domains [6]. The case of meaning management and cognition in artificial agents is rather straightforward with the MGS approach as we, the designers, know the agents and the constraints. In addition, our evolutionary approach brings to position notions like artificial constraints, meaning and autonomy as derived from their animal or human source. We next highlight that cognition as management of meaningful information by agents goes beyond information and needs to address representations which belong to the central hypothesis of cognitive sciences. We define the meaningful representation of an item for an agent as being the networks of meanings relative to the item for the agent, with the action scenarios involving the item. Such meaningful representations embed the agents in their environments and are far from the GOFAI type ones [4]. Meanings, representations and cognition exist by and for the agents. We finish by summarizing the points presented and highlight some possible continuations. [1] C. Menant "Information and Meaning" http://cogprints.org/3694/ [2] C. Menant “Introduction to a Systemic Theory of Meaning” (short paper) http://crmenant.free.fr/ResUK/MGS.pdf [3] A. Weber and F. Varela “Life after Kant: Natural purposes and the autopoietic foundations of biological individuality”. Phenomenology and the Cognitive Sciences 1: 97–125, 2002. [4] C. Menant "Computation on Information, Meaning and Representations. An Evolutionary Approach" http://www.idt.mdh.se/ECAP-2005/INFOCOMPBOOK/CHAPTERS/10-Menant.pdf http://crmenant.free.fr/2009BookChapter/C.Menant.211009 [5] C. Menant "Proposal for a shared evolutionary nature of language and consciousness" http://cogprints.org/7067/ [6] Philpapers “philosophy of mind” http://philpapers.org/browse/philosophy-of-mind

Before the modern computing era, the word `computers' referred to human beings as living calculators---in fact, still Turing (1950) proposed his test for A.I. referring to `computing machinery', not `computers'. From the advent of general-purpose, Turing-complete machines the relation between operators, programmers and users with computers---inforgs, in Floridi's terms---can be seen in terms of levels of abstraction (LoA) (Floridi 2010, 2008). For example, the modern concept of `operating system' (Donovan 1974) by Ken Thompson from Multics to Unix can be seen as a level of abstraction: some computational tasks are hidden in an abstract machine put into the computer system so that humans can forget it instead of manually perform the task as living operators: information got hidden, without being lost. In this paper an analysis of LoA throughout history is proposed, in order to find the minimal number of LoAs needed to explain the epistemology of informational organisms (inforgs)---from early modern general-purpose computing machineries until the so-called `cloud computing'. This epistemological levellism uses Category Theory as the methodological reference, treating information as structure-preserving functions instead of Cartesian products, i.e., a domain mapped into a codomain where the inner structure is preserved; a comparison with the method of LoA by Floridi (2008) is then proposed.

In this paper we present a novel strategy to discover the community structure of (possibly, large) networks. This approach is based on the well-know concept of network modularity optimization. To do so, our algorithm exploits a novel measure of edge centrality, based on the k-paths. This technique allows to efficiently compute a edge ranking in large networks in near linear time. Once the centrality ranking is calculated, the algorithm computes the pairwise proximity between nodes of the network. Finally, it discovers the community structure adopting a strategy inspired by the well-known state-of-the-art Louvain method (henceforth, LM), efficiently maximizing the network modularity. The experiments we carried out show that our algorithm outperforms other techniques and slightly improves results of the original LM, providing reliable results. Another advantage is that its adoption is naturally extended even to unweighted networks, differently with respect to the LM.

The amount of information available on the Web grows at an incredible high rate. Systems and procedures devised to extract these data from Web sources already exist, and different approaches and techniques have been investigated during the last years. On the one hand, reliable solutions should provide robust algorithms of Web data mining which could automatically face possible malfunctioning or failures. On the other, in literature there is a lack of solutions about the maintenance of these systems. Procedures that extract Web data may be strictly interconnected with the structure of the data source itself; thus, malfunctioning or acquisition of corrupted data could be caused, for example, by structural modifications of data sources brought by their owners. Nowadays, verification of data integrity and maintenance are mostly manually managed, in order to ensure that these systems work correctly and reliably. In this paper we propose a novel approach to create procedures able to extract data from Web sources -- the so called Web wrappers -- which can face possible malfunctioning caused by modifications of the structure of the data source, and can automatically repair themselves.

Matrix Factorization techniques have been successfully applied to raise the quality of suggestions generated by Collaborative Filtering Systems (CFSs). Traditional CFSs based on Matrix Factorization operate on the ratings provided by users and have been recently extended to incorporate demographic aspects such as age and gender. In this paper we propose to merge CF techniques based on Matrix Factorization and information regarding social friendships in order to provide users with more accurate suggestions and rankings on items of their interest. The proposed approach has been evaluated on a real-life online social network; the experimental results show an improvement against existing CF approaches. A detailed comparison with related literature is also present

In this paper we present a novel strategy to discover the community structure of (possibly, large) networks. This approach is based on the well-know concept of network modularity optimization. To do so, our algorithm exploits a novel measure of edge centrality, based on the k-paths. This technique allows to efficiently compute a edge ranking in large networks in near linear time. Once the centrality ranking is calculated, the algorithm computes the pairwise proximity between nodes of the network. Finally, it discovers the community structure adopting a strategy inspired by the well-known state-of-the-art Louvain method (henceforth, LM), efficiently maximizing the network modularity. The experiments we carried out show that our algorithm outperforms other techniques and slightly improves results of the original LM, providing reliable results. Another advantage is that its adoption is naturally extended even to unweighted networks, differently with respect to the LM.

The amount of information available on the Web grows at an incredible high rate. Systems and procedures devised to extract these data from Web sources already exist, and different approaches and techniques have been investigated during the last years. On the one hand, reliable solutions should provide robust algorithms of Web data mining which could automatically face possible malfunctioning or failures. On the other, in literature there is a lack of solutions about the maintenance of these systems. Procedures that extract Web data may be strictly interconnected with the structure of the data source itself; thus, malfunctioning or acquisition of corrupted data could be caused, for example, by structural modifications of data sources brought by their owners. Nowadays, verification of data integrity and maintenance are mostly manually managed, in order to ensure that these systems work correctly and reliably. In this paper we propose a novel approach to create procedures able to extract data from Web sources -- the so called Web wrappers -- which can face possible malfunctioning caused by modifications of the structure of the data source, and can automatically repair themselves.

Social (or folksonomic) tagging has become a very popular way to describe content within Web 2.0 websites. Unlike taxonomies, which overimpose a hierarchical categorisation of content, folksonomies enable end-users to freely create and choose the categories (in this case, tags) that best describe some content. However, as tags are informally de- fined, continually changing, and ungoverned, social tagging has often been criticised for lowering, rather than increasing, the efficiency of searching, due to the number of synonyms, homonyms, polysemy, as well as the heterogeneity of users and the noise they introduce. To address this issue, a variety of approaches have been proposed that recommend users what tags to use, both when labelling and when looking for resources. As we illustrate in this paper, real world folksonomies are characterized by power law distributions of tags, over which commonly used similarity metrics, including the Jaccard coefficient and the cosine similarity, fail to compute. We thus propose a novel metric, specifically developed to capture similarity in large-scale folksonomies, that is based on a mutual reinforcement principle: that is, two tags are deemed similar if they have been associated to similar resources, and vice-versa two resources are deemed similar if they have been labelled by similar tags. We offer an efficient realisation of this similarity metric, and assess its quality experimentally, by comparing it against cosine similarity, on three large-scale datasets, namely Bibsonomy, MovieLens and CiteULike.

Nowadays, the huge amount of information distributed through the Web motivates studying techniques to be adopted in order to extract relevant data in an efficient and reliable way. Both academia and enterprises developed several approaches of Web data extraction, for example using techniques of artificial intelligence or machine learning. Some commonly adopted procedures, namely wrappers, ensure a high degree of precision of information extracted from Web pages, and, at the same time, have to prove robustness in order not to compromise quality and reliability of data themselves. In this paper we focus on some experimental aspects related to the robustness of the data extraction process and the possibility of automatically adapting wrappers. We discuss the implementation of algorithms for finding similarities between two different version of a Web page, in order to handle modifications, avoiding the failure of data extraction tasks and ensuring reliability of information extracted. Our purpose is to evaluate performances, advantages and draw-backs of our novel system of automatic wrapper adaptation.

Natural Language Parsing has been the most prominent research area since the genesis of Natural Language Processing. Probabilistic Parsers are being developed to make the process of parser development much easier, accurate and fast. In Indian context, identification of which Computational Grammar Formalism is to be used is still a question which needs to be answered. In this paper we focus on this problem and try to analyze different formalisms for Indian languages.

It is common wisdom in the area of adult education that the educator's relational attitudes influence knowledge construction on the part of the learners. It is the aim of this paper to contribute to an empirical evaluation of this idea. We identified four basic relational attitudes of the educator's, namely: (i) favoring cooperation, (ii) directivity, (iii) flexibility, and (iv) ability to focus on the participants. Then, we identified 31 prototypical types of behavior that are commonly enacted by educators in the classroom. We performed multiple observations of several adult education courses, scoring each educator on the list of 31 behavior types. We performed factor analysis and then correlated such scores and the corresponding attitudes to indexes of the participants' levels of attention, participation and comprehension. The results corroborate our hypotheses. Interestingly, several differences was found between novice and expert teachers. Overall, our findings support the socio-constructivist idea that knowing is a transformational process of learning that takes place within a relational context.

This paper investigates the effectiveness of creative versus uncreative leadership using EVOC, an agent-based model of cultural evolution. Each iteration, each agent in the artificial society invents a new action, or imitates a neighbor’s action. Only the leader’s actions can be imitated by all other agents, referred to as followers. Two measures of creativity were used: (1) invention-to-imitation ratio, iLeader, which measures how often an agent invents, and (2) rate of conceptual change, cLeader, which measures how creative an invention is. High iLeader increased mean fitness of ideas, but only when creativity of followers was low. High iLeader was associated with greater diversity of ideas in the early stage of idea generation only. High Leader increased mean fitness of ideas in the early stage of idea generation; in the later stage it decreased idea fitness. Reasons for these findings and tentative implications for creative leadership in human society are discussed.

Companions as interfaces to smart rooms need not only to be easy to interact with, but also to maintain long-term relationships with their users. The FP7-funded project SERA (Social Engagement with Robots and Agents) contributes to knowledge about and modeling of such relationships. One focal activity is an iterative field study to collect real-life long-term interaction data with a robotic interface. The first stage of this study has been completed. This paper reports on the set-up and the first insights.

This paper demonstrates that simple yet important characteristics of coevolution can occur in evolutionary algorithms when only a few conditions are met. We find that interaction-based fitness measurements such as fitness (linear) ranking allow for a form of coevolutionary dynamics that is observed when 1) changes are made in what solutions are able to interact during the ranking process and 2) evolution takes place in a multi-objective environment. This research contributes to the study of simulated evolution in a at least two ways. First, it establishes a broader relationship between coevolution and multi-objective optimization than has been previously considered in the literature. Second, it demonstrates that the preconditions for coevolutionary behavior are weaker than previously thought. In particular, our model indicates that direct cooperation or competition between species is not required for coevolution to take place. Moreover, our experiments provide evidence that environmental perturbations can drive coevolutionary processes; a conclusion that mirrors arguments put forth in dual phase evolution theory. In the discussion, we briefly consider how our results may shed light onto this and other recent theories of evolution.

At various machine learning conferences, at various times, there have been discussions arising from the inability to replicate the experimental results published in a paper. There seems to be a wide spread view that we need to do something to address this problem, as it is essential to the advancement of our field. The most compelling argument would seem to be that reproducibility of experimental results is the hallmark of science. Therefore, given that most of us regard machine learning as a scientific discipline, being able to replicate experiments is paramount. I want to challenge this view by separating the notion of reproducibility, a generally desirable property, from replicability, its poor cousin. I claim there are important differences between the two. Reproducibility requires changes; replicability avoids them. Although reproducibility is desirable, I contend that the impoverished version, replicability, is one not worth having.

According to recent studies in developmental psychology and neuroscience, symbolic language is essentially intersubjective. Empathetically relating to others renders possible the acquisition of linguistic constructs. Intersubjectivity develops in early ontogenetic life when interactions between mother and infant mutually shape their relatedness. Empirical findings suggest that the shared attention and intention involved in those interactions is sustained as it becomes internalized and embodied. Symbolic language is derivative and emerges from shared intentionality. In this paper, we present a formalization of shared intentionality based upon a quantum approach. From a phenomenological viewpoint, we investigate the nonseparable, dynamic and sustainable nature of social cognition and evaluate the appropriateness of quantum interaction for modelling intersubjectivity.

Small firms are indeed the engines of global economic growth. Small and Medium Enterprises (SMEs) play an important role to promote economic development. SMEs in the beginning of implementing new technologies always face capital shortage and need technological assistance. Available ERP systems do not fulfil the specific requirements of Small firms. SMEs has scarce resources and manpower therefore many SMEs don?t have the possessions to buy and operate an ERP System. On the other hand competition and competitiveness of SMEs have to be strengthened. This paper briefly reviews the existing perspectives on virtual teams and their effect on SMEs management. It also discusses the main characteristics of virtual teams and clarifies the differences aspects of virtual team application in SMEs. After outlining some of the main advantages and pitfall of such teams, it concentrates on comparing of ERP and virtual collaborative teams in SMEs. Finally, it provides evidence for the need of ?Software as a Service (SaaS)? where an application is hosted as a service provided to customers across the web for SMEs as an alternative of ERP. It has been widely argued that ERP disadvantage in SMEs such as administrative expenditure and cost, isolated structure, severe lack of software flexibility, insufficient support of SMEs business and high operating cost, lead SMEs to use virtual collaborative team which is net work base solution.

Recognizing analogies, synonyms, antonyms, and associations appear to be four distinct tasks, requiring distinct NLP algorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four semantic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algorithms for each semantic phenomenon; we need to seek a unified approach. We propose to subsume a broad range of phenomena under analogies. To limit the scope of this paper, we restrict our attention to the subsumption of synonyms, antonyms, and associations. We introduce a supervised corpus-based machine learning algorithm for classifying analogous word pairs, and we show that it can solve multiple-choice SAT analogy questions, TOEFL synonym questions, ESL synonym-antonym questions, and similar-associated-both questions from cognitive psychology.

Evolutionary algorithms are commonly used to create high-performing strategies or agents for computer games. In this paper, we instead choose to evolve the racing tracks in a car racing game. An evolvable track representation is devised, and a multiobjective evolutionary algorithm maximises the entertainment value of the track relative to a particular human player. This requires a way to create accurate models of players' driving styles, as well as a tentative definition of when a racing track is fun, both of which are provided. We believe this approach opens up interesting new research questions and is potentially applicable to commercial racing games.

A perceived limitation of evolutionary art and design algorithms is that they rely on human intervention; the artist selects the most aesthetically pleasing variants of one generation to produce the next. This paper discusses how computer generated art and design can become more creatively human-like with respect to both process and outcome. As an example of a step in this direction, we present an algorithm that overcomes the above limitation by employing an automatic fitness function. The goal is to evolve abstract portraits of Darwin, using our 2nd generation fitness function which rewards genomes that not just produce a likeness of Darwin but exhibit certain strategies characteristic of human artists. We note that in human creativity, change is less choosing amongst randomly generated variants and more capitalizing on the associative structure of a conceptual network to hone in on a vision. We discuss how to achieve this fluidity algorithmically.

In this paper, a new method for assigning credit to search operators is presented. Starting with the principle of optimizing search bias, search operators are selected based on an ability to create solutions that are historically linked to future generations. Using a novel framework for defining performance measurements, distributing credit for performance, and the statistical interpretation of this credit, a new adaptive method is developed and shown to outperform a variety of adaptive and non-adaptive competitors.

In this paper, the issue of adapting probabilities for Evolutionary Algorithm (EA) search operators is revisited. A framework is devised for distinguishing between measurements of performance and the interpretation of those measurements for purposes of adaptation. Several examples of measurements and statistical interpretations are provided. Probability value adaptation is tested using an EA with 10 search operators against 10 test problems with results indicating that both the type of measurement and its statistical interpretation play significant roles in EA performance. We also find that selecting operators based on the prevalence of outliers rather than on average performance is able to provide considerable improvements to adaptive methods and soundly outperforms the non-adaptive case.

In an attempt to illustrate the application of cognitive science principles to hard AI problems in machine learning we propose the LIDA technology, a cognitive science based architecture capable of more human-like learning. A LIDA based software agent or cognitive robot will be capable of three fundamental, continuously active, humanlike learning mechanisms: 1) perceptual learning, the learning of new objects, categories, relations, etc., 2) episodic learning of events, the what, where, and when, 3) procedural learning, the learning of new actions and action sequences with which to accomplish new tasks. The paper argues for the use of modular components, each specializing in implementing individual facets of human and animal cognition, as a viable approach towards achieving general intelligence.

In this paper we present the LIDA architecture as a working model of cognition. We argue that such working models are broad in scope and address real world problems in comparison to experimentally based models which focus on specific pieces of cognition. While experimentally based models are useful, we need a working model of cognition that integrates what we know from neuroscience, cognitive science and AI. The LIDA architecture provides such a working model. A LIDA based cognitive robot or software agent will be capable of multiple learning mechanisms. With artificial feelings and emotions as primary motivators and learning facilitators, such systems will ‘live’ through a developmental period during which they will learn in multiple ways to act in an effective, human-like manner in complex, dynamic, and unpredictable environments. We discuss the integration of the learning mechanisms into the existing IDA architecture as a working model of cognition.