Search

Artificial intelligence (AI) policy, innovation, and practice are moving ahead in rapid fashion. There is a growing mismatch between technological innovations in AI, which are advancing at a rapid rate, and normative and regulatory frameworks, which are lagging, particularly when it comes to protecting democratic values and human rights principles. National governments and multilateral institutions are attempting to catch up. At least 175 countries, firms and other organizations have produced documents listing ethical principles for AI. These efforts have proceeded in a somewhat fragmented manner, yet there are emerging signs of consolidation as the United States, Europe, and other countries begin to coalesce around shared principles. Europe, in particular, has raced ahead to draft comprehensive legislation, the Artificial Intelligence Act (AIA), to oversee these technologies and systems. What has motivated the European Union to pursue this approach? And how will this effort influence AI norms globally? This paper describes how Europe's AI norm-building process represents an effort to ensure EU priorities are reflected in the AI governance landscape. Europe's approach faces uncertainty. While it is likely that the AIA will meaningfully influence global AI norms, several factors may hinder its global diffusion and adoption. [ABSTRACT FROM AUTHOR]

To optimize anthropogenic material streams, the production process, as well as the quality of the products, must be known. With knowledge of these requirements, it is possible to use extra applied algorithms—in this case evolutionary algorithms as part of artificial intelligence—for the optimization of these secondary material streams. The benefit of this application is the fast and precise calculation of the local and global optima of the optimizing problem. This calculation method uses the benefits of the biological reproduction by applications of mutation, selection, and recombination to find one of the best results in a huge amount of possible and potential results. For the use of secondary materials in the paper production it could be proven that in spite of high quotes of secondary materials in different paper classes, there are some paper classes in which the amount of secondary material could be raised without losing any quality. [ABSTRACT FROM AUTHOR]

This paper undertakes a comparative analysis of the famous eighteenth-century chess-playing automaton known as Mechanical Turk and the Amazon microwork platform of the same name. The original Mechanical Turk was a life-sized automaton made in 1770 and publicly exhibited until the mid-1800s, and which played games of chess with the audience. Its movements were fully mechanical, but even more remarkably, it was promoted as the world's first 'thinking machine,' deciding each move of the chess pieces for itself. From the outset, it was widely assumed that the Mechanical Turk was a hoax, and that a human must be hidden inside the machine, directing the game. But it was a clever hoax whose trick was never discovered, and widely admired as such. Amazon's Mechanical Turk job platform functions in a similarly open way, this paper argues, as a sort of open technological hoax. Mechanical Turk provides a source of human cognitive labour that can be used to invisibly operate digital systems and programs that are widely assumed to be fully automated. Artificial intelligence is a twenty-first century thinking machine, it requires a human brain to make it work. Amazon's Mechanical Turk is a marketplace in which companies can hire piecemeal cognitive labour to patch gaps and train programs to keep those systems functioning. Providing what Jeff Bezos has called 'artificial artificial intelligence,' Amazon's Mechanical Turk, like Kempelen's automaton, both draws attention to and obfuscates the limits of automation and artificial intelligence. Taking the two iterations of the Mechanical Turk as rich cultural figures of automation for their respective periods, this paper will argue that the open secret of their artificial artificial intelligence is itself a form of misdirection that hides other, more successfully guarded secrets: the true extent of that labour, and the conditions in which it is performed. [ABSTRACT FROM AUTHOR]

The article presents selected papers from the CIPS Edmonton 1987 Conference that was held in Edmonton, Alberta on November 16-19, 1987. The theme of the event was Intelligence Integration. The Program Committee's aim is to emphasize the integration of intelligence into computer applications, the application of intelligence to the integration of software components and the development of intelligent tools that would aid the process of system integration. A second unique feature of the event is its balanced treatment of invited and submitted paper presentations. The submitted papers were selected to complement the invited papers by providing technical information as well as indicating future research directions.

This paper describes a single-machine scheduling problem of maximizing total job value with a machine availability constraint. The value of each job decreases over time in a stepwise fashion. Several solution properties of the problem are developed. Based on the properties, a branch-and-bound algorithm and a heuristic algorithm are derived. These algorithms are evaluated in the computational study, and the results show that the heuristic algorithm provides effective solutions within short computation times. [ABSTRACT FROM AUTHOR]

The thought-provoking EPSRC Principles of Robotics stem largely from the reflection on the extent to which robots can affect our lives. These comments highlight the fact that, while the principles may address to a good extent the present technological challenges, they appear to be less immediately suited for future technological and conceptual dares. The first part of the paper is dedicated to the search of the definition of what a robot is. Such a definition should offer the basic conceptual platform on which a normative endeavour, aiming to regulate robots in society, should be based. Concluding that the Principles offer no clear yet flexible insight into such a (meta-) definition, which would allow one to take into account the parameters of informed technological imagination and of envisaged social transformation, the second half of the paper highlights a number of regulatory points of tension. Such tensions, it is argued, stem largely from the absence of an appropriate conceptual platform, influencing negatively the extent to which the principles can be effective in guiding social, ethical, legal and scientific conduct. [ABSTRACT FROM PUBLISHER]

This paper presents a new method to discover transition rules of geographical cellular automata (CA) based on a bottom-up approach, ant colony optimization (ACO). CA are capable of simulating the evolution of complex geographical phenomena. The core of a CA model is how to define transition rules so that realistic patterns can be simulated using empirical data. Transition rules are often defined by using mathematical equations, which do not provide easily understandable explicit forms. Furthermore, it is very difficult, if not impossible, to specify equation-based transition rules for reflecting complex geographical processes. This paper presents a method of using ant intelligence to discover explicit transition rules of urban CA to overcome these limitations. This 'bottom-up' ACO approach for achieving complex task through cooperation and interaction of ants is effective for capturing complex relationships between spatial variables and urban dynamics. A discretization technique is proposed to deal with continuous spatial variables for discovering transition rules hidden in large datasets. The ACO-CA model has been used to simulate rural-urban land conversions in Guangzhou, Guangdong, China. Preliminary results suggest that this ACO-CA method can have a better performance than the decision-tree CA method. [ABSTRACT FROM AUTHOR]

Support vector machines can be used in a new machine learning technique based on statistical learning. In this paper, we develop least squares support vector machines (LS-SVMs) using the lazy learning approach to classify data in unclassifiable regions in the case of multi-class classification. LS-SVMs use a set of linear equations while SVMs use a quadratic programming problem. The lazy learning approach is a local and memory-based technique. Therefore, it is an alternative technique to fuzzy inference systems. Our studies show that LS-SVMs with the lazy learning approach can give comparable results to fuzzy LS-SVMs for multi-class classification. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the limitations of current evolutionary robotics models and we propose a new framework that might solve some of these problems and lead to art open-ended evolutionary process in hardware. More specifically, the paper describes a novel approach where the usual concepts of population, generations and fitness tire made implicit in the system. Individuals co-evolve embedded in their environment. Exploiting the sell-assembling capabilities of the (simulated) robots, the genotype of a successful individual can spread in the population. In this way, interesting behaviours emerge spontaneously, resulting in chasing and evading other individuals, collective obstacle avoidance and co-ordinated motion of self-assembled structures. [ABSTRACT FROM AUTHOR]

Modeling the environment and agent-environment relationships is not well explored in multi-agent systems, in particular not for software multi-agent systems. This paper aims to contribute with a generic model for active perception in situated multi-agent systems. Active perception enables an agent to direct its perception at the most relevant aspects in the environment, according to its current task. The model decomposes perception into three functionalities: sensing, interpreting, and filtering.The agent first senses its neighborhood through a set of selected foci, resulting in a representation. A set of perceptual laws enforces domain specific constraints on sensing. Next, the agent interprets the representation by means of descriptions, resulting in a percept. Percepts are expressions that can be understood by the internal machinery of the agent. Finally, the percept is filtered by a set of selected filters, restricting the perceived data according to specific context relevant selection criteria. [ABSTRACT FROM AUTHOR]

Case-based reasoning systems, in general, and instance-based reasoning systems, in particular, are used more and more in industrial applications nowadays. During the last few years, researchers have been working in the development of techniques to automate the reasoning stages identified in this methodology. This paper presents a method for automating the retrieval stage and indexation of instance-based reasoning systems. This method is based on a modification of a new type of topology preserving map that can be used for scale invariant classification. The scale invariant map is an implementation of the negative feedback network to form a topology-preserving mapping. Maximum/minimum likelihood learning is applied in this paper to the scale invariant map and its possibilities are explored. This method automates the organization of cases and the retrieval stage of case-based reasoning systems. The proposed methodology groups instances with similar structure, identifying clusters automatically in a data set in an unsupervised mode. The method has been successfully used to completely automate the reasoning process of an oceanographic forecasting system and to improve its performance. [ABSTRACT FROM AUTHOR]

Earlier studies indicated that using multiple dispatching rules (MDRs) for the various zones in the system can enhance the production performance to a greater extent than using a single dispatching rule (SDR) over a given scheduling interval for all the machines in the system, since MDRs employ the multi-pass simulation approach for real-time scheduling (RTS). However, if a classical machine learning approach is used, an RTS knowledge base (KB) can be developed by using the appropriate MDRs strategy (this method is called an intelligent multi-controller in this paper) as obtained from training examples. The main disadvantage of using MDRs is that the classes (scheduling decision variables) to which training examples are assigned must be provided. Hence, developing an RTS KB using the intelligent multi-controller approach becomes an intolerably time-consuming task because MDRs for the next scheduling period must be determined. To address this issue, we proposed an intelligent multi-controller incorporating three main mechanisms: (1) simulation-based training example generation mechanism, (2) data pre-processing mechanism and (3) SOM-based real time MDRs selection mechanism. Under various performance criteria over a long period, the proposed approach yields better system performance than the machine learning-based RTS using the SDR approach and heuristic individual dispatching rules. [ABSTRACT FROM AUTHOR]

Does acquiring artificial intelligence (AI) technologies from the US or China render countries more authoritarian or technologically less advantageous? In this article, we explore to what extent importing AI/high-tech from the US and/or China goes parallel with importers' (a) democratization or autocratization, (b) state capacity, and (c) technological progress across a decade (2010–2020). Our work demonstrates that not only are Chinese AI/high-tech exports not congruous with importers' democratic backsliding, but autocratization attributed to Chinese AI is also visible in importers of US AI. In addition, for most indicators, we do not observe any significant effect of acquiring AI from the US or China on importers' state capacity or technological progress across the same period. Instead, we find that the story has a global inequality dimension as Chinese exports are clustered around countries with a lower GDP per capita, whereas US high-technology exports are clustered around relatively wealthier states with slightly weaker capacity over territorial control. Overall, the article empirically demonstrates the limitations of some of the prevalent policy discourses surrounding the global diffusion of AI and its contribution to democratization, state capacity, and technological development of importer nations. [ABSTRACT FROM AUTHOR]

This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed totheconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test. [ABSTRACT FROM AUTHOR]

The random subspace method (RSM) has proved its excellence in numbers of pattern recognition tasks. However, the standard RSM is limited owing to the randomness in its feature selection procedure that is likely to lead to feature subset having poor class separability. In this paper, a proposal for a margin-based criterion has been presented for the evaluation of the true significance of the features, together with the true classification ability of base classifiers, so that both the training phase and integration phase of standard RSM could be enhanced. In the training phase, the random feature selection procedure is enhanced using a weighted random feature selection procedure, in order to improve the classification ability of the base classifier. In the integration phase, the simple majority voting strategy is enhanced using a weighted majority voting strategy for the purpose of assigning the base classifiers with poor classification ability to the lower voting weights. Experimental results on 30 benchmark datasets, together with 6 high-dimensional datasets prove that the recommended approach is capable of better providing classification ability to the usual classification task, in addition to the high-dimensional classification task. [ABSTRACT FROM AUTHOR]

The features related to the real world data may be redundant and erroneous in nature. The vital role of feature selection (FS) in handling such type of features cannot be ignored in the area of computational learning. The two most commonly used objectives for FS are the maximisation of the accuracy and minimisation of the number of features. This paper presents an Elitism-based Multi-objective Differential Evolution algorithm for FS and the novelty lies in the searching process which uses Minkowski Score (MS) and simultaneously optimises three objectives. The MS is considered as the third objective to keep track of the feature subset which is capable enough to produce a good classification result even if the average accuracy is poor. Extreme Learning Machine because of its fast learning speed and high efficiency has been considered with this multi-objective approach as a classifier for FS. Twenty-one benchmark datasets have been considered for performance evaluation. Moreover, the selected feature subsets are tested using 10-fold cross-validation. A comparative analysis of the proposed approach with two classical models, three single objective algorithms, and four multi-objective algorithms has been carried out to test the efficacy of the model. [ABSTRACT FROM AUTHOR]

Domain independent planning engines accept a planning task description in a language such as PDDL and return a solution plan. Performance of planning engines can be improved by gathering additional knowledge about a class of planning tasks. In this paper we present Outer Entanglements, relations between planning operators and predicates, that are used to restrict the number of operator instances. Outer Entanglements can be encoded within a planning task description, effectively reformulating it. We provide an in depth analysis and evaluation of outer entanglements illustrating the effectiveness of using them as generic heuristics for improving the efficiency of planning engines. [ABSTRACT FROM AUTHOR]

The accurate forecasting of solar irradiance with hybrid machine learning algorithm is presented in this paper. A novel Persistence-Extreme Learning Machine (P-ELM) algorithm is used for training of the system. The Clearness Index (CI) value of the 22 districts of Andhra Pradesh (India) is calculated and out of which four areas are identified with highest CI values. The Global Horizontal Irradiance (GHI) is forecasted for the selected areas with different weather conditions such as winter, summer and rainfall seasons using a P-ELM algorithm. The input parameters are Temperature, Diffuse horizontal irradiance, pressure and past GHI and GHI for the next instant as the output is considered. The real time data is obtained for every one hour interval for a period of one month. The performance of the P-ELM algorithm is evaluated in terms of Mean Absolute Error and Root Mean Square Error. From the obtained results, it is observed that P-ELM algorithm offers better performance over the fundamental P-ELMs. The P-ELM algorithm gives good forecasting accuracy with minimum simulation time. The simulation of P-ELM algorithm is carried out using MATLAB 2013a environment. The P-ELM algorithm is very much beneficial for accurate and reliable real time solar forecasting. [ABSTRACT FROM AUTHOR]

This paper deals with aiding preliminary design when considered as a constraint satisfaction problem (CSP). In this case, constraint filtering techniques provide some kind of interactive assistance to the designer. However, some kinds of numerical constraints corresponding with numerical relations cannot be filtered precisely with classical analytical filtering techniques such as interval arithmetic or box-consistency; it is therefore necessary to discretize them in order to include them in the CSP. To this end, quad trees (QT) have been proposed for binary constraints, or 2k trees when more than two variables are considered; but QT assume that a constraint must be defined by a single numerical function. The aim of this paper is to show that QT techniques can be extended when a constraint is defined by a piecewise function or by a set of numerical functions defined on intervals. The first section recalls some basics relevant to the preliminary design problem and the interests of the CSP assistance. The second section presents the principles of the QT. The last section describes our contributions relevant to QT extensions dealing with piecewise functions. [ABSTRACT FROM AUTHOR]

Conceptual clustering plays an important role in machine learning. In this paper, we propose a quasi-clustering method, network classification, which improves upon the computational efficiency of traditional conceptual clustering methods. Network classification is based on the Power Law assumption and the concept of hub observations/instances. The method is evaluated in several domains and compared with examples of both unsupervised learning and supervised learning methods. The results show that network classification maintains a comparable forecasting accuracy, while exhibiting an improved computing performance over conceptual clustering methods. [ABSTRACT FROM AUTHOR]

This paper extends research in the area of biologically inspired, discrete dynamical basis networks (DDBNs). While similar to locally recurrent globally feed forward (LRGF) networks (Tsoi and Back 1994). DDBNs operate at a lower level of abstraction and were inspired by research in the areas of Control Systems. Artificial Intelligence and Neurobiology, As described previously, DDBNs can approximate data sequences and consist of networks of simple, bounded mathematical operators (Jones and Olmsted 2003). This paper examines the characteristics of genetically designed DDBNs and compares them with tree-based genetic programs (TBGPs), biological neural networks, and backpropagation neural networks (NNs). Experimental evidence indicates that DDBNs are capable of computing simple logic functions in addition to approximating data sequences. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the problem of having a multitude of very simple mobile robots self-organize their relative positions so as to obtain a variety of spatial configurations. The problem has a variety of applications in mobile robotics, modular robots, sensor networks, and computational self-assembly. The approach we investigate in this paper attempts at minimizing the local capability of robots and at verifying how and to what extent a variety of global shapes can be obtained by exploiting simple self-organizing algorithms and emergent behaviors. Several experiments are reported showing the effectiveness of the approach. [ABSTRACT FROM AUTHOR]

This paper again presses the case for computationalism by considering the latest in ill-conceived attacks on this foundational idea. The authors briefly but clearly define and delimit computationalism and then consider three authors from a new anti-computationalist collection. [ABSTRACT FROM AUTHOR]

Can a computer play a music score, e.g. via a Disklavier, in a way that cannot be distinguished from a human performance of the same music? One hundred and seventy-two participants with a wide range of music playing backgrounds rated sound recordings of 7 performances of piano music by Kuhlau, one played by a human, and six generated by algorithms, including a ‘mechanical’ and an ‘unmusical’ rendering. Participants rated the extent to which each performance was by a human and explained their answers. The mechanical performance had the lowest mean rating, but the human performance was rated as statistically identical to the other stimuli. There were no differences between ratings made by classical piano experts and lay listeners, but despite this, the musicians were more confident with their ratings. Qualitative analysis revealed five broad themes that contribute to judging whether a piece appears to be human. The themes were labelled (in descending order of frequency) intuitive, expressive, imperfections, halo (global preference) and empathy. This paper presents new evidence systematically demonstrating that algorithm generated performances of piano music can be indistinguishable from human performances, suggesting some parallels with the 1990s victory of the Deep Blue computer of the world champion (human) chess player. [ABSTRACT FROM AUTHOR]

This paper presents the development of an intelligent predictive tool for improving the accuracy of parts produced on CNC turning centers. Actual dimensions and shape (form) produced on components during machining differ from the nominal dimensions commanded in the CNC program. These dimensional and form errors on parts depend on a variety of factors such as tool/work deflections, machine tool accuracy, machining conditions etc. These errors, if predicted, can be used to correct the ideal CNC code and thus improve the part accuracy in CNC machining. In the present work artificial neural networks are used to capture the complex relationship between the errors on the component and the input process conditions. Significant improvement in part accuracy has been obtained using the corrected CNC code during machining. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses various reports within the issue on topics including artificial intelligence (AI), technology and machine ethics.

For providing a feasible solution for real-time terrain classification using ICESat-2 data, a supervised machine-learning-based real-time terrain classification method using ICESat data is proposed, which is composed of two procedures: offline classifier training and online terrain classification. The first procedure is accomplished by true label generation and feature selection. We advanced a new method of true label generation that uses laser-footprint-scale slopes and waveform characteristics as input data. The laser-footprint-scale slopes are estimated by an improved slope estimation method using elevations of repeat tracks. For feature selection, several waveform characteristics are extracted and the best ones are selected based on experiments. Using the generated true labels and selected features, we train a support vector machine classifier for the second procedure and the performance of online terrain classification is tested using ICESat/GLAS data collected from Beijing area during 2003–2009. The results show that by carefully selecting the features, high classification accuracy (around 92.36%) can be achieved even if the feature dimension is significantly reduced. Furthermore, the classification time of one laser footprint, which is approximately equal to 0.006 s, is less than one laser shot time; thus, the proposed method can be used for real-time terrain classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new information-theoretic method to measure the comprehensibility of network configurations in competitive learning. Comprehensibility is supposed to be measured by information contained in components in competitive networks. Thus, the increase in information corresponds to the increase in comprehensibility of network configurations. One of the most important characteristics of the method is that parameters can be explicitly determined so as to produce a state where the different types of comprehensibility can be mutually increased. We applied the method to two problems, namely an artificial data set and the ionosphere data from the well-known machine learning database. In both problems, we showed that improved performance could be obtained in terms of all types of comprehensibility and quantization errors. For the topographic errors, we found that updating connection weights prevented them from increasing. Then, the optimal values of comprehensibility could be explicitly determined, and clearer class boundaries were generated. [ABSTRACT FROM AUTHOR]

Activity recognition (AR) has become a hot research topic due to its strength in providing personalized support for many diverse applications such as healthcare and security. Due to its importance, a considerable amount of AR systems have been developed. In general, these systems utilize diverse sensors to obtain the activity related information, which are then used by machine learning techniques to infer human's ongoing activity. According to the types of sensors used, existing AR systems can be roughly divided into two categories: 1. Video sensor based AR. It remotely observes human activity using video sensors; 2. Physical sensor based AR (PSAR). It attaches physical sensors to the body of human or objects (appliances) to infer human activity. Based on the location of attached sensors, PSAR consists of two subcategories: Wearable sensor based AR and object usage based AR. In this work, different types of AR are reviewed. We think this review is significant because no existing review papers include all the different types of AR as a whole. For each type of AR, its main techniques, characteristics, strengths and limitations are discussed and summarized. We also make a comparative analysis for them. Finally the main research challenges in AR are pointed out. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs) have become one of the most powerful methods in machine learning for solving classification and regression problems. Finding the SVM solution can be regarded as estimating the centre of the largest hypersphere that can be inscribed in the set of consistent hypotheses called the version space. However, this solution can be inaccurate if the version space is asymmetric or elongated. Several approaches have been proposed to utilize other possible centres of the version space that can improve the generalization performance. Morreti in 2003 proposed an algorithm for finding the centre of a general polytope, the so called p-Centre, using weighted projections. By applying this method, Bruckner in 2001 introduced a formulation for solving binary classification problems based on an approximation of the p-Centre of the version space, the so called p-Centre machine. In this paper, we extend the work by Bruckner and propose a kernel-based algorithm for regression analysis using the p-Centre method. The concept of the p-Centre of a polytope and version space is also explained. Furthermore, the applications of the proposed method are presented. The preliminary results indicate that the p-Centre-based kernel machine for regression has promising performance compared with the SVM for regression. [ABSTRACT FROM AUTHOR]

This paper proposes a combination of differential evolution (DE) and estimation of distribution algorithm (EDA) to design photonic crystal fiber structures with desired properties over the C communication band. In order to determine the properties of PCFs such as dispersion, dispersion slope and loss, an artificial intelligence method, the Nero-Fuzzy system, is applied. In addition, a special cost function which simultaneously includes the confinement loss, dispersion and its slope is used in the proposed design approach. The results revealed that the proposed method is a powerful tool for solving this optimization problem. The optimized PCF exhibits an ultra low confinement loss and low dispersion at 1.55 µm wavelength with a nearly zero dispersion slope over the C communication band. [ABSTRACT FROM AUTHOR]

In recent years, advances and improvements in engineering and robotics have in part been due to strengthened interactions with the biological sciences. Robots that mimic the complexity and adaptability of biological systems have become a central goal in research and development in robotics. Usually, such a collaboration is addressed to a 2-fold perspective of (i) setting up anthropomorphic platforms as test beds for studies in neuroscience and (ii) promoting new mechatronic and robotic technologies for the development of bio-inspired or humanoid high-performance robotic platforms. This paper provides a brief overview of recent studies on sensorimotor coordination in human motor control and proposes a novel paradigm of adaptive learning for sensorimotor control, based on a multi-network high-level control architecture. The proposed neurobiologically inspired model has been applied to a robotic platform, purposely designed to provide anthropomorphic solutions to neuroscientific requirements. The goal of this work is to use the bio-inspired robotic platform as a test bed for validating the proposed model of high-level sensorimotor control, with the aim of demonstrating adaptive and modular control based on acquired competences, with a higher degree of flexibility and generality than conventional robotic controllers, while preserving their robustness. To this purpose, a set of object-dependent, visually guided reach-and-grasp tasks and the associated training phases were first implemented in a multi-network control architecture in simulation. Subsequently, the offline learning realized in simulation was used to produce the input command of reach-and-grasp to the low-level position control of the robotic platform. Experimental trials demonstrated that the adaptive and modular high-level control allowed reaching and grasping of objects located at different positions and objects of variable size, shape and orientation. A future goal would be to address autonomous and progressive learning based on growing competences. [ABSTRACT FROM AUTHOR]

In this paper, we analyze the different approaches taken to date within the computer vision, robotics and artificial intelligence communities for the representation, recognition, synthesis and understanding of action. We deal with action at different levels of complexity and provide the reader with the necessary related literature references. We put the literature references further into context and outline a possible interpretation of action by taking into account the different aspects of action recognition, action synthesis and task-level planning. [ABSTRACT FROM AUTHOR]

Multi-representational reasoning processes often show a variety of reasoning paths that can be followed. To analyze such reasoning processes with special attention for differences between individuals, it is required (1) to obtain an overview of the variety of different possibilities and (2) to address navigation and control within the reasoning process. This paper presents a simulation model and a formal analysis method for the dynamics of a controlled reasoning process in which multiple representations play a role. Reasoning strategies to navigate through the space of possible reasoning states are modeled explicitly, and simulated. Simulation results are analyzed by software tools on the basis of formalized dynamic properties. The variety of dynamic properties specified and the variety of traces simulated provides an overview for the individual differences between subjects that have been observed while solving multiplication problems. [ABSTRACT FROM AUTHOR]

The expression "artificial intelligence" (AI) was introduced by John McCarthy, and the official birth of AI is unanimously considered to be the 1956 Dartmouth Conference. Thus, AI turned fifty in 2006. How did AI begin? Several differently motivated analyses have been proposed as to its origins. In this paper a brief look at those that might be considered steps towards Dartmouth is attempted, with the aim of showing how a number of research topics and controversies that marked the short history of AI were touched on, or fairly well stated, during the year immediately preceding Dartmouth. The framework within which those steps were taken was the development of digital computers. Earlier computer applications in areas such as complex decision making and management, at that time dealt with by operations research techniques, were important in this story. The time was ripe for AI's intriguingly tumultuous development, marked as it has been by hopes and defeats, successes and difficulties. [ABSTRACT FROM AUTHOR]

The last decade has seen a considerable growth in the use of Artificial Intelligence (Al) for operations management with the aim of finding solutions to problems that are increasing in complexity and scale. This paper begins by setting the context for the survey through a historical perspective of OR and Al. An extensive survey of applications of Al techniques for operations management, covering a total of over 1200 papers published from 1995 to 2004 is then presented. The survey utilizes Elsevier's ScienceDirect database as a source. Hence, the survey may not cover all the relevant journals but includes a sufficiently wide range of publications to make it representative of the research in the field. The papers are categorized into four areas of operations management: (a) design, (b) scheduling, (c) process planning and control and (d) quality, maintenance and fault diagnosis. Each of the four areas is categorized in terms of the Al techniques used: genetic algorithms, case-based reasoning, knowledge-based systems, fuzzy logic and hybrid techniques. The trends over the last decade are identified, discussed with respect to expected trends and directions for future work suggested. [ABSTRACT FROM AUTHOR]

The need for intelligent systems has grown in the past decade because of the increasing demand on humans and machines to perform better. The researchers of artificial intelligence (AI) have responded to these needs with the development of intelligent hybrid systems. This paper describes the modeling language for interacting hybrid systems in which we will build a new hybrid model of cellular automata and multiagent technology. Simulations with complex behavior will be model social dynamics where the focus is on the emergence of properties of local interactions. Therefore, in our approach, cellular automata form a useful framework for the multiagent simulation model and the model will be used for traffic system which lies in coordinating the local behavior of individual agent to provide an appropriate system-level behavior in grid of interacting organisms. [ABSTRACT FROM AUTHOR]

In this paper we describe an application of Q 2 learning, a recently developed approach to machine learning in numerical domains (Šuc et al., 20032004) to the automated modelling of a complex, industrially relevant mechanical system – a four wheel suspension and steering system of a car. In this experiment, first a qualitative model of this dynamic system was induced from data, and then this model was reified into a quantitative model. The induced qualitative models enable explanation of relations among the variables in the system and, when reified into quantitative models, enable accurate numerical prediction. Furthermore, the qualitative guidance of the quantitative modelling process leads to predictions that are significantly more accurate than those obtained by state-of-the-art numerical learning methods. [ABSTRACT FROM AUTHOR]

This paper argues that fuzzy representations are appropriate in applications where there are major sources of imprecision and/or uncertainty. Case studies of fuzzy approaches to specific problems of medical diagnosis and classification are described in support of this argument. The case studies are in the areas of categorical consistency, diagnostic monitoring, and scoring. the solutions use a variety of fuzzy methods, including clustering, fuzzy set aggregation, and type-2 fuzzy set modeling of linguistic approximations. It is concluded that the fuzzy approach to the development of artificial intelligence in application systems in beneficial in these contexts because of the need to focus an uncertainty as a main issue. [ABSTRACT FROM AUTHOR]

Many researchers in embodied cognitive science and artificial intelligence, and evolutionary robotics in particular, emphasize the interaction or brain, body and environment as crucial to the emergence of intelligent. adaptive behaviour. Accordingly. the interaction between agent and environment. as well as the co-adaptation of artificial brains and bodies, has been the focus of much research in evolutionary robotics. Hence, there are plenty of studies of robotic agents/species adapting to a given environment. Many animals, on the other hand, in particular humans, to some extent can choose to adapt the environment to their own needs instead of adapting (onIy) themselves. That alternative has been studied relatively little in robot experiments. This paper, therefore, presents some simple initial simulation experiments, in a delayed response task setting, that illustrate how the evolution of environment adaptation can sent to provide cognitive scaffolding that reduces the requirements for individual agents. Furthermore, theoretical implications, open questions and future research directions for evolutionary robotics are discussed. [ABSTRACT FROM AUTHOR]

This paper presents some techniques for analogical mapping using associative-projective neural networks (APNNs). Sparse binary distributed representations of constant high dimensionality are constructed on-the-fly for hierarchical structures of various complexity. Such representations encode both surface and structural similarity of analogical episodes. The introduced mapping approaches are illustrated using test analogies. [ABSTRACT FROM AUTHOR]

Berkeley et al. (1995, Connection Science, 7: 167–186) introduced a novel technique for analysing the hidden units of connectionist networks that had been trained using the backpropagation learning procedure. The literature concerning banding analysis is equivocal with respect to the kinds of processing units this technique can be used on. In this paper, it will be shown that, contrary to the claims in some published sources, banding analysis can be conducted on networks that use standard processing units that have a sigmoid activation function. The analytic process is then illustrated and the potential benefits of this kind of technique are discussed. [ABSTRACT FROM AUTHOR]

While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. This is not just implausible cognitively, but disastrous practically. However, it is not easy in connectionist cognitive modelling to keep away from highly distributed neural networks, if only because of their ability to generalize. A realistic and effective system that solves the problem of catastrophic interference in sequential learning of ‘static’ (i.e. non-temporally ordered) patterns has been proposed recently (Robins 1995. Connection Science. 7: 123–146, 1996. Connection Science, 8: 259–275, Ans and Rousset 1997. CR Académie ties Sciences Paris. Life Sciences, 320: 989–997, French 1997, Connection Science. 9: 353–379, 1999, Trends in Cognitive Sciences, 3: 128–135, Ans and Rousset 2000, Connection Science, 12: 1–19). The basic principle is to learn new external patterns interleaved with internally generated ‘pseudopatterns’ (generated from random activation) that reflect the previously learned information. However, to be credible, this self-refreshing mechanism for static learning has to encompass our human ability to learn serially many temporal sequences of patterns without catastrophic forgetting. Temporal sequence learning is arguably more important than static pattern learning in the real world. In this paper, we develop a dual-network architecture in which self-generated pseudopatterns reflect (non-temporally) all the sequences of temporally ordered items previously learned. Using these pseudopatterns, several self-refreshing mechanisms that eliminate catastrophic forgetting in sequence learning are described and their efficiency is demonstrated through simulations. Finally, an experiment is presented that evidences a close similarity between human and simulated behaviour. [ABSTRACT FROM AUTHOR]

A reason maintenance system (RMS) has been in use for representation of actions. This paper presents an architecture that handles both action and time in a framework while preserving the advantages of both RMS and temporal constraint propagation(TCP). This framework captures action as well as temporal knowledge in the network in terms of relations between intervals. Thus it enables integration of temporal reasoning along with causal reasoning among activities. An algorithm for truth propagation in such a network has been applied to a specific domain, and an example illustrating its use in temporal and causal reasoning is provided. Abstraction of activities and states has been done by defining abstract temporal intervals and thus layering the knowledge into various levels. Some relational abstractions which are useful in describing the temporal relationships among activities and facts have also been defined. [ABSTRACT FROM AUTHOR]

The paper presents a novel evolutionary technique constructed as an alternative of the standard support vector machines architecture. The approach adopts the learning strategy of the latter but aims to simplify and generalize its training, by offering a transparent substitute to the initial black-box. Contrary to the canonical technique, the evolutionary approach can at all times explicitly acquire the coefficients of the decision function, without any further constraints. Moreover, in order to converge, the evolutionary method does not require the positive (semi-)definition properties for kernels within nonlinear learning. Several potential structures, enhancements and additions are proposed, tested and confirmed using available benchmarking test problems. Computational results show the validity of the new approach in terms of runtime, prediction accuracy and flexibility. [ABSTRACT FROM AUTHOR]

There is great potential in enabling users to interact with digital information by integrating it with everyday physical objects. However, developing these interfaces requires programmers to acquire and abstract physical input. This is difficult, is time-consuming, and requires a high level of technical expertise in fields very different from user interface development—especially in the case of computer vision. Based on structured interviews with researchers, a literature review, and our own experience building physical interfaces, we created Papier-Mache, a toolkit for integrating physical and digital interactions. Its library supports computer vision, electronic tags, and barcodes. Papier-Mache introduces high-level abstractions for working with these input technologies that facilitate technology portability. We evaluated this toolkit through a laboratory study and longitudinal use in course and research projects, finding the input abstractions, technology portability, and monitoring facilities to be highly effective. [ABSTRACT FROM AUTHOR]

In this paper, the method of understanding of visual objects is presented. The main novelty of the presented method is that the process of understanding is related to the visual concept represented as a symbolic name of the possible classes of shapes. The possible classes of shapes, viewed as hierarchical structures, are incorporated into the shape model. At each stage of the reasoning process that led to assigning an examined object to one of the possible classes, novel processing methods are used. An understanding is based on interpretation of the visual object as a meaningful unit. A big advantage of the proposed method of understanding of the visual objects is that it can explain many problems connected with understanding visual forms. In this paper, the selected concept of the method of understanding of the visual objects is discussed in the context of the psychological and philosophical research. This method is implemented as a module of the shape understanding system (SUS) and tested on the broad classes of shapes. [ABSTRACT FROM AUTHOR]

Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multistate searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process. [ABSTRACT FROM AUTHOR]

The field of Artificial General Intelligence needs a simple and understandable measure of progress to aid in passing the difficult Turing Test. The proposed Ladder Metric introduces a sequence of levels that intelligent agents must climb in order to reach the final, Turing indistinguishable, level. Just like the Turing test, the levels can only be defined in terms of general properties and behaviour rather than specific operational requirements. To track the progress and make comparisons one must climb and determine the achieved rung of the proposed ladder. [ABSTRACT FROM AUTHOR]

Robots and chatbots are sophisticated. Artificial intelligence (AI) is increasingly popular in the financial industry due to its ability to provide customers with cheap, efficient and personalised services. This article uses doctrinal sources and a case study to show that many banks and FinTech start-ups are investing in AI. Yet, there are a number of challenges arising from the use of AI which could undermine trust and confidence amongst consumers. This article features the issue of bias and discrimination in banking. There is evidence that algorithms discriminate against certain races and gender. Legislative gaps in the Equality Act 2010 and the General Data Protection Regime will be analysed. Ultimately, human beings are still needed to input, train and help machines to learn. Fortunately, the FCA are leading in regulating technology, from the launch of regulatory sandboxes to their co-operative collaboration with FinTech start-ups on regulatory matters. Augmented intelligence collaboration is needed to enable industry players and regulators to provide seamless regulation and financial stability. The future of AI regulation is inter-disciplinary in approach. [ABSTRACT FROM AUTHOR]