Search

Recently, computational thinking (CT) has gained importance in education systems worldwide, specifically the CT training of pre-service teachers. This study conducted a systematic literature analysis (2011–2021) of 38 works on pre-service teachers' CT based on Web of Science, Science Direct, and Google Scholar databases. The results were as follows: (1) Six training methods were found, (2) CT training effectively improved pre-service teachers' CT, (3) A positive relationship was found between pre-service teachers' CT ability and the five factors affecting the ability, (4) A mode of training to improve CT ability of pre-service teachers and the relationship between CT ability and teaching methods were considered. This study suggested ideas for designing training modules of CT ability and a reference for realizing the best training effect. Finally, future research trends and a general model of training were presented as references for researchers, instructors, and policy makers to promote the CT of pre-service teachers. [ABSTRACT FROM AUTHOR]

Recent findings show that goals affect the way in which agents represent their environment, choose relevant actions, and subjectively evaluate outcomes as rewards. Because goals influence all aspects of decision-making and learning, developing a complete theory thereof requires that we understand how agents select their goals. While computational research on goal generation and management is in its early stages, existing studies suggest that goal selection may be framed as a value-based decision-making process, with values acquired via direct experience or inference, combined with directed and undirected selection policies. Goals play a central role in human cognition. However, computational theories of learning and decision-making often take goals as given. Here, we review key empirical findings showing that goals shape the representations of inputs, responses, and outcomes, such that setting a goal crucially influences the central aspects of any learning process: states, actions, and rewards. We thus argue that studying goal selection is essential to advance our understanding of learning. By following existing literature in framing goal selection within a hierarchy of decision-making problems, we synthesize important findings on the principles underlying goal value attribution and exploration strategies. Ultimately, we propose that a goal-centric perspective will help develop more complete accounts of learning in both biological and artificial agents. [ABSTRACT FROM AUTHOR]

The brain learns representations of sensory information from experience, but the algorithms by which it does so remain unknown. One popular theory formalizes representations as inferred factors in a generative model of sensory stimuli, meaning that learning must improve this generative model and inference procedure. This framework underlies many classic computational theories of sensory learning, such as Boltzmann machines, the Wake/Sleep algorithm, and a more recent proposal that the brain learns with an adversarial algorithm that compares waking and dreaming activity. However, in order for such theories to provide insights into the cellular mechanisms of sensory learning, they must be first linked to the cell types in the brain that mediate them. In this study, we examine whether a subtype of cortical interneurons might mediate sensory learning by serving as discriminators, a crucial component in an adversarial algorithm for representation learning. We describe how such interneurons would be characterized by a plasticity rule that switches from Hebbian plasticity during waking states to anti-Hebbian plasticity in dreaming states. Evaluating the computational advantages and disadvantages of this algorithm, we find that it excels at learning representations in networks with recurrent connections but scales poorly with network size. This limitation can be partially addressed if the network also oscillates between evoked activity and generative samples on faster timescales. Consequently, we propose that an adversarial algorithm with interneurons as discriminators is a plausible and testable strategy for sensory learning in biological systems. Author summary: After raw sensory data is received at the periphery, it is transformed by various neural pathways and delivered to the sensory cortex. There, neural activity forms an internal model of the state of the external world, which is updated appropriately by new information. A goal of learning, then, is to learn how to transform information into the appropriate representational form within the brain's internal model. Here, we look to artificial intelligence for new possible theories of how the brain might learn representations that resolve issues with previously proposed theories. We describe how one particular algorithm—adversarial learning—resolves a major issue with previous hypotheses relating to recurrence. Furthermore, this algorithm resembles broad features of the organization and learning dynamics of the brain, such as wake and sleep cycles. Considering seriously how this algorithm would appear if implemented by the brain, we map its features to known physiology and make testable predictions for how neural circuits learn new representations of information. [ABSTRACT FROM AUTHOR]

Formal models of learning from teachers need to respect certain criteria to avoid collusion. The most commonly accepted notion of collusion-avoidance was proposed by Goldman and Mathias (1996), and various teaching models obeying their criterion have been studied. For each model M and each concept class C, a parameter M-TD(C) refers to the teaching dimension of concept class C in model M--defined to be the number of examples required for teaching a concept, in the worst case over all concepts in C. This paper introduces a new model of teaching, called no-clash teaching, together with the corresponding parameter NCTD(C). No-clash teaching is provably optimal in the strong sense that, given any concept class C and any model M obeying Goldman and Mathias's collusion-avoidance criterion, one obtains NCTD(C) ≤ M-TD(C). We also study a corresponding notion NCTD+ for the case of learning from positive data only, establish useful bounds on NCTD and NCTD+, and discuss relations of these parameters to other complexity parameters of interest in computational learning theory. We further argue that Goldman and Mathias's collusion-avoidance criterion may in some settings be too weak in that it admits certain forms of interaction between teacher and learner that could be considered collusion in practice. Therefore, we introduce a strictly stronger notion of collusion-avoidance and demonstrate that the well-studied notion of Preference-based Teaching is optimal among all teaching schemes that are strongly collusion-avoiding on all finite subsets of a given concept class. [ABSTRACT FROM AUTHOR]

Numerous computational and learning theory models have been studied using probabilistic functional equations. Especially in two-choice scenarios, the vast bulk of animal behavior research divides such situations into two different events. They split these actions into two possibilities according to the animals' progress toward a particular decision. However, reward plays a crucial role in such experiments because, based on the selected side and the food placement, such scenarios may be classified into four distinct categories. This article aims to explore the animals' reactions to such circumstances by presenting a generic stochastic functional equation. By using the well-known fixed point theory results, we examine the existence, uniqueness, and stability of solutions to the suggested functional equation. Moreover, an example is included to emphasize the significance of our findings. [ABSTRACT FROM AUTHOR]

Declarative process modeling formalisms—which capture high-level process constraints—have seen growing interest, especially for modeling flexible processes. This paper presents DisCoveR, an efficient and accurate declarative miner for learning Dynamic Condition Response (DCR) Graphs from event logs. We present a precise formalization of the algorithm, describe a highly efficient bit vector implementation and present a preliminary evaluation against five other miners, representing the state-of-the-art in declarative and imperative mining. DisCoveR performs competitively with each of these w.r.t. a fully automated binary classification task, achieving an average accuracy of 96.1% in the Process Discovery Contest 2019 (Results are available at https://icpmconference.org/2019/process-discovery-contest). We appeal to computational learning theory to gain insight into its performance as a classifier. Due to its linear time complexity, DisCoveR also achieves much faster run times than other declarative miners. Finally, we show how the miner has been integrated in a state-of-the-art declarative process modeling framework as a model recommendation tool and discuss how discovery can play an integral part of the modeling task and report on how the integration has improved the modeling experience of end-users. [ABSTRACT FROM AUTHOR]

Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in high-dimensional data analysis and unsupervised learning. While polynomial time smoothed analysis guarantees have been obtained for worst-case intractable problems like tensor decomposition and learning mixtures of Gaussians, such guarantees have been hard to obtain for several other important problems in data analysis. A core technical challenge in analyzing algorithms is obtaining lower bounds on the least singular value for random matrix ensembles with dependent entries, that are given by low-degree polynomials of a few base underlying random variables. In this work, we address this challenge by obtaining high-confidence lower bounds on the least singular value of new classes of structured random matrix ensembles of the above kind. We then use these bounds to design algorithms with polynomial time smoothed analysis guarantees for the following three important problems in high-dimensional data analysis: Higher order tensor decompositions, where we generalize and analyze the so-called FOOBI algorithm of Cardoso. This allows us to obtain polynomially robust decomposition algorithms for 2 ℓ 'th order tensors with rank O (n ℓ) . Learning overcomplete hidden markov models, where the size of the state space is any polynomial in the dimension of the observations. This gives the first polynomial time guarantees for learning overcomplete HMMs in the smoothed analysis model. Robust subspace recovery, when the fraction α of inliers in the d-dimensional subspace T ⊂ R n is at least α > (d / n) ℓ for any constant ℓ ∈ Z + . This contrasts with the known worst-case intractability when α < d / n , and the previous smoothed analysis result which needed α > d / n ([33]). [ABSTRACT FROM AUTHOR]

This article examines the resource sharing functionality of the decryption platform of Europol. The platform supports European law enforcement agencies (LEAs) that are having difficulties accessing legally obtained encrypted evidence due to the lack of human and technical resources. The article investigates Europol's resource transmission role with sharing economy variables such as transaction cost and trust-building. The core argument of the article is that Europol's sharing platform has a strong potential to reduce the transaction cost of outsourcing the decryption services and diminish trust-related problems for national policing agencies by replacing private sector actors. However, for a more sustainable cybercrime investigation strategy, the decryption platform needs a new market-oriented model supported with robust vetting and evidence security mechanisms to encourage more private company participation. [ABSTRACT FROM AUTHOR]

This paper presents a novel, sequentially executed supervised machine learning‐based electric theft detection framework using a Jaya‐optimized combined Kernel and Tree Boosting (KTBoost) classifier. It utilizes the intelligence of the XGBoost algorithm to estimate the missing values in the acquired dataset during the data pre‐processing phase. An oversampling algorithm based on the Robust‐SMOTE technique is utilized to avoid the unbalanced data class distribution issue. Afterward, with the aid of few very significant statistical, temporal, and spectral features extracted from the acquired kWh dataset, the complex underlying data patterns are comprehended to enhance the accuracy and detection rate of the classifier. For effectively classifying the consumers into "Honest" and "Fraudster," the ensemble machine learning‐based classifier KTBoost, with Jaya algorithm optimized hyperparameters, is utilized. Finally, the developed model is re‐trained using a reduced set of highly important features to minimize the computational resources without compromising the performance of the developed model. The outcome of this study reveals that the proposed theft detection method achieves the highest accuracy (93.38%), precision (95%), and recall (93.18%) among all the studied methods, thus signifying its importance in the studied area of research. [ABSTRACT FROM AUTHOR]

We show that the topes of a complex of oriented matroids (abbreviated COM) of VC-dimension d admit a proper labeled sample compression scheme of size d. This considerably extends results of Moran and Warmuth on ample classes, of Ben-David and Litman on affine arrangements of hyperplanes, and of the authors on complexes of uniform oriented matroids, and is a step towards the sample compression conjecture – one of the oldest open problems in computational learning theory. On the one hand, our approach exploits the rich combinatorial cell structure of COMs via oriented matroid theory. On the other hand, viewing tope graphs of COMs as partial cubes creates a fruitful link to metric graph theory. [ABSTRACT FROM AUTHOR]

Quantum computation requires large classical datasets to be embedded into quantum states in order to exploit quantum parallelism. However, this embedding requires considerable resources in general. It would therefore be desirable to avoid it, if possible, for noisy intermediate-scale quantum (NISQ) implementation. Accordingly, we consider a classical-quantum hybrid architecture, which allows large classical input data, with a relatively small-scale quantum system. This hybrid architecture is used to implement a sampling oracle. It is shown that in the presence of noise in the hybrid oracle, the effects of internal noise can cancel each other out and thereby improve the query success rate. It is also shown that such an immunity of the hybrid oracle to noise directly and tangibly reduces the sample complexity in the framework of computational learning theory. This NISQ-compatible learning advantage is attributed to the oracle's ability to handle large input features. [ABSTRACT FROM AUTHOR]

This article aims to bring contributions about the use of Pierre Rabardel's Instrumental Approach, as an effective theoretical framework in the development of studies by researchers who are interested in the analysis of technological tools and their potentialities that intervene in the subject's relationship (researcher, Professor3 and/or student), with the objects of knowledge through the mediation of these tools, aiming at mathematical learning. In the applications, we give special attention to digital technological tools, choosing the GeoGebra software as a computational learning environment, observing the theoretical elements of this approach in two dimensions, which we define as internal research and external research. We therefore propose an extension of the Instrumental Activity Situations (IAS) model in three dimensions, motivating a reflection on the role of the Professor or researcher in the primitive relations of this model in external research, during its application in the classroom. We hope that our contributions/reflections find a significant space in the development of educational research, especially in science and mathematics using Rabardel's Instrumental Approach [ABSTRACT FROM AUTHOR]

This article aims to bring contributions about the use of Pierre Rabardel's Instrumental Approach, as an effective theoretical framework in the development of studies by researchers who are interested in the analysis of technological tools and their potentialities that intervene in the subject's relationship (researcher, Professor3 and/or student), with the objects of knowledge through the mediation of these tools, aiming at mathematical learning. In the applications, we give special attention to digital technological tools, choosing the GeoGebra software as a computational learning environment, observing the theoretical elements of this approach in two dimensions, which we define as internal research and external research. We therefore propose an extension of the Instrumental Activity Situations (IAS) model in three dimensions, motivating a reflection on the role of the Professor or researcher in the primitive relations of this model in external research, during its application in the classroom. We hope that our contributions/reflections find a significant space in the development of educational research, especially in science and mathematics using Rabardel's Instrumental Approach. [ABSTRACT FROM AUTHOR]

In real life, the increased data accessing speed and data storage ability is required by most of the machinery fields. However, the real-world problems can be studied effectively with the combination of scientific computational techniques with the mathematical models. Automata theory is known to be the popular mathematical model. Towards most of the software and hardware related applications, the computational methods are analyzed and designed using significant automata theory concepts (likely, pushdown automata (PDA), Turing machines (TMs) and finite automata (FA)). Hence, the conventional lecture-driven style has attracted the reflective preferences of learners using these abstract natured concepts. But the lecture-driven teaching style has less motivated the computer engineering learners. In order to learn automata theory and computational models, we introduce the PDA and TM in a virtual platform. However, this work has motivated the improvement of longitudinal experimental validation and learning using the modern technology. Java Formal Languages and Automata Package (JFLAP) tool is used to write our simulators in JAVA language and the results are obtained from each machine through simulating the input strings. [ABSTRACT FROM AUTHOR]

Shape, texture, and color are critical features for assessing the degree of dysplasia in colonic polyps. A comprehensive analysis of these features is presented in this paper. Shape features are extracted using generic Fourier descriptor. The nonsubsampled contourlet transform is used as texture and color feature descriptor, with different combinations of filters. Analysis of variance (ANOVA) is applied to measure statistical significance of the contribution of different descriptors between two colonic polyps: non-neoplastic and neoplastic. Final descriptors selected after ANOVA are optimized using the fuzzy entropy-based feature ranking algorithm. Finally, classification is performed using Least Square Support Vector Machine and Multi-layer Perceptron with five-fold cross-validation to avoid overfitting. Evaluation of our analytical approach using two datasets suggested that the feature descriptors could efficiently designate a colonic polyp, which subsequently can help the early detection of colorectal carcinoma. Based on the comparison with four deep learning models, we demonstrate that the proposed approach out-performs the existing feature-based methods of colonic polyp identification. [ABSTRACT FROM AUTHOR]

It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of adversarially robust learning from the perspective of computational learning theory, considering both sample and computational complexity. In particular, our definition of robust learnability requires polynomial sample complexity. We start with two negative results. We show that no non-trivial concept class can be robustly learned in the distribution-free setting against an adversary who can perturb just a single input bit. We show, moreover, that the class of monotone conjunctions cannot be robustly learned under the uniform distribution against an adversary who can perturb !(log n) input bits. However, we also show that if the adversary is restricted to perturbing O(log n) bits, then one can robustly learn the class of 1-decision lists (which subsumes monotone conjunctions) with respect to the class of log-Lipschitz distributions. We then extend this result to show learnability of 2-decision lists and monotone k-decision lists in the same distributional and adversarial setting. Finally, we provide a simple proof of the computational hardness of robust learning on the boolean hypercube. Unlike previous results of this nature, our result does not rely on a more restricted model of learning, such as the statistical query model, nor on any hardness assumption other than the existence of an (average-case) hard learning problem in the PAC framework; this allows us to have a clean proof of the reduction, and the assumption is no stronger than assumptions that are used to build cryptographic primitives. [ABSTRACT FROM AUTHOR]

The article presents a critical response to Ted Underwood's article "The Theoretical Divide Driving Debates about Computation." Topics discussed include definition and meaningful uses of exploratory data analysis; Leif Weatherby's concept of the bottleneck in Computational Literary Studies; and his push for a theory of data and information redundancy in it instead; and literature's irreducible complexity.

The article presents a critical response to Nan Z. Da's article "The Computational Case against Computational Literary Studies" which focuses on data-based interpretation. It mentions that she singled out computational literary studies from digital humanities, including histories of media and early computational practices, the digitization of texts for open access, digital inscription and mediation, and computational linguistics and lexicology, and technical papers on data mining.

The article presents a critical response to Nan Z. Da's article "The Computational Case against Computational Literary Studies." It mentions that mathematical approaches to literature must fail on mathematical grounds. It also mentions that research should be based on public code and data that is as public as possible under copyright law.

The problem of learning Boolean linear functions from quantum examples w.r.t. the uniform distribution can be solved on a quantum computer using the Bernstein–Vazirani algorithm (Bernstein and Vazirani, in: Kosaraju (ed) Proceedings of the twenty-fifth annual ACM symposium on theory of computing, ACM, New York, 1993. 10.1145/167088.167097). A similar strategy can be applied in the case of noisy quantum training data, as was observed in Grilo et al. (Learning with errors is easy with quantum samples, 2017). However, extensions of these learning algorithms beyond the uniform distribution have not yet been studied. We employ the biased quantum Fourier transform introduced in Kanade et al. (Learning dnfs under product distributions via μ -biased quantum Fourier sampling, 2018) to develop efficient quantum algorithms for learning Boolean linear functions on n bits from quantum examples w.r.t. a biased product distribution. Our first procedure is applicable to any (except full) bias and requires O (ln (n)) quantum examples. The number of quantum examples used by our second algorithm is independent of n, but the strategy is applicable only for small bias. Moreover, we show that the second procedure is stable w.r.t. noisy training data and w.r.t. faulty quantum gates. This also enables us to solve a version of the learning problem in which the underlying distribution is not known in advance. Finally, we prove lower bounds on the classical and quantum sample complexities of the learning problem. Whereas classically, Ω (n) examples are necessary independently of the bias, we are able to establish a quantum sample complexity lower bound of Ω (ln (n)) only under an assumption of large bias. Nevertheless, this allows for a discussion of the performance of our suggested learning algorithms w.r.t. sample complexity. With our analysis, we contribute to a more quantitative understanding of the power and limitations of quantum training data for learning classical functions. [ABSTRACT FROM AUTHOR]

Pattern languages have been an object of study in various subfields of computer science for decades. This paper introduces and studies a decision problem on patterns called the finite distinguishability problem: given a pattern π , are there finite sets T + and T − of strings such that the only pattern language containing all strings in T + and none of the strings in T − is the language generated by π ? This problem is related to the complexity of teacher-directed learning, as studied in computational learning theory, as well as to the long-standing open question whether the equivalence of two patterns is decidable. We show that finite distinguishability is decidable if the underlying alphabet is of size other than 2 or 3, and provide a number of related results, such as (i) partial solutions for alphabet sizes 2 and 3, and (ii) decidability proofs for variants of the problem for special subclasses of patterns, namely, regular, 1-variable, and non-cross patterns. For the same subclasses, we further determine the values of two complexity parameters in teacher-directed learning, namely the teaching dimension and the recursive teaching dimension. [ABSTRACT FROM AUTHOR]

Artificial neural networks grow on the number of applications and complexity, which require a minimization on the number of units for some practical implementations. A particular problem is the minimum number of units that a feed forward neural network needs on its first layer. In order to study this problem, it is defined a family of classification problems following a continuity hypothesis, where inputs that are close to some set of points may share the same category. Given a set S of k −dimensional inputs and let N be a feed forward neural network that classifies any input in S within a fixed error, there is proved that N requires Θ k units in the first layer, if N can solve any instance from the given family of classification problems. Furthermore, this asymptotic result is optimal. [ABSTRACT FROM AUTHOR]

Highlights • A new algorithm to compute the moments defined in a rectangular region is developed. • It is verified that our computational method can efficiently and accurately compute Legendre, Gegenbauer, and Jacobi moments. • With our new algorithm, using the higher orders of moments defined in a rectangular region in real-time image analysis and recognition applications will be possible. Abstract In this research, we have developed a new algorithm to compute the moments defined in a rectangular region. By applying the recurrent formulas, symmetry properties, and particularly the parallelized matrix operations, our proposed computational method can improve the efficiency of computing Legendre, Gegenbauer, and Jacobi moments extensively with highly satisfied accuracy. To verify this new computational algorithm, the image reconstructions from the higher orders of Legendre, Gegenbauer, and Jacobi moments are performed on a testing image sized at 1024 × 1024 with very encouraging results. It took only a few seconds to compute moments and conduct the image reconstructions from the 1000-th order of the Legendre, Gegenbauer, and Jacobi moments with the PSNR values up to 45. By utilizing our new algorithm, image analysis and recognition applications using the higher orders of moments defined in a rectangular region in the range of milliseconds will be possible. [ABSTRACT FROM AUTHOR]

The problem of learning the solution space of an unknown formula has been studied in multiple embodiments in computational learning theory. In this article, we study a family of such learning problems; this family contains, for each relational structure, the problem of learning the solution space of an unknown conjunctive query evaluated on the structure. A progression of results aimed to classify the learnability of each of the problems in this family, and thus far a culmination thereof was a positive learnability result generalizing all previous ones. This article completes the classification program towards which this progression of results strived, by presenting a negative learnability result that complements the mentioned positive learnability result. In addition, a further negative learnability result is exhibited, which indicates a dichotomy within the problems to which the first negative result applies. In order to obtain our negative results, we make use of universal-algebraic concepts. [ABSTRACT FROM AUTHOR]

Pater's (2019) target article proposes that neural networks will provide theories of learning that generative grammar lacks. We argue that his enthusiasm is premature since the biases of neural networks are largely unknown, and he disregards decades of work on machine learning and learnability. Learning biases form a two-way street: all learners have biases, and those biases constrain the space of learnable grammars in mathematically measurable ways. Analytical methods from the related fields of computational learning theory and grammatical inference allow one to study language learning, neural networks, and linguistics at an appropriate level of abstraction. The only way to satisfy our hunger and to make progress on the science of language learning is to confront these core issues directly. [ABSTRACT FROM AUTHOR]

The notion of a fast uplink grant is emerging as a promising solution for enabling massive machine type communication (MTC) in the Internet of Things over cellular networks. By using the fast uplink grant, machine type devices (MTDs) will no longer require RA channels to send scheduling requests. Instead, uplink resources can be actively allocated to MTDs by a base station. In this article, the challenges and opportunities for adopting the fast uplink grant to support MTCs are investigated. First, the fundamentals of fast uplink grant and its advantages over conventional scheduled and uncoordinated access schemes are presented. Then, the key challenges that include the prediction of the set of MTDs with data to transmit, as well as the optimal scheduling of MTDs, are exposed. To overcome these challenges, a two-stage approach that includes traffic prediction and optimized scheduling is proposed. In particular, various solutions for source traffic prediction for periodic MTC traffic are reviewed and novel methods for event-driven traffic prediction are proposed. For optimal allocation of uplink grants, advanced machine learning techniques are presented. By using the proposed solutions, the fast uplink grant has the potential to enable cellular networks to support massive MTCs and effectively reduce the signaling overhead and overcome the delay and congestion challenges of conventional RA schemes. [ABSTRACT FROM AUTHOR]

Human beliefs have remarkable robustness in the face of disconfirmation. This robustness is often explained as the product of heuristics or motivated reasoning. However, robustness can also arise from purely rational principles when the reasoner has recourse to ad hoc auxiliary hypotheses. Auxiliary hypotheses primarily function as the linking assumptions connecting different beliefs to one another and to observational data, but they can also function as a "protective belt" that explains away disconfirmation by absorbing some of the blame. The present article traces the role of auxiliary hypotheses from philosophy of science to Bayesian models of cognition and a host of behavioral phenomena, demonstrating their wide-ranging implications. [ABSTRACT FROM AUTHOR]

Abstract The rank aggregation problem has received significant recent attention within the computer science community. Its applications today range far beyond the original aim of building metasearch engines to problems in machine learning, recommendation systems and more. Several algorithms have been proposed for these problems, and in many cases approximation guarantees have been proven for them. However, it is also known that some Markov chain based algorithms (MC1, MC2, MC3, MC4) perform extremely well in practice, yet had no known performance guarantees. We prove supra-constant lower bounds on approximation guarantees for all of them. Nevertheless, we show that in particular ways, MC4 can be seen as a generalization of Copeland score. [ABSTRACT FROM AUTHOR]

Boosting algorithms have been proved effective for multi-label learning. As ensemble learning algorithms, boosting algorithms build classifiers by composing a set of weak hypotheses. The high computational cost of boosting algorithms in learning from large volumes of data such as text categorization datasets is a real challenge. Most boosting algorithms, such as AdaBoost.MH, iteratively examine all training features to generate the weak hypotheses, which increases the learning time. RFBoost was introduced to manage this problem based on a rank-and-filter strategy in which it first ranks the training features and then, in each learning iteration, filters and uses only a subset of the highest-ranked features to construct the weak hypotheses. This step ensures accelerated learning time for RFBoost compared to AdaBoost.MH, as the weak hypotheses produced in each iteration are reduced to a very small number. As feature ranking is the core idea of RFBoost, this paper presents and investigates seven feature ranking methods (information gain, chi-square, GSS-coefficient, mutual information, odds ratio, F1 score, and accuracy) in order to improve RFBoost's performance. Moreover, an accelerated version of RFBoost, called RFBoost1, is also introduced. Rather than filtering a subset of the highest-ranked features, FBoost1 selects only one feature, based on its weight, to build a new weak hypothesis. Experimental results on four benchmark datasets for multi-label text categorization) Reuters-21578, 20-Newsgroups, OHSUMED, and TMC2007(demonstrate that among the methods evaluated for feature ranking, mutual information yields the best performance for RFBoost. In addition, the results prove that RFBoost statistically outperforms both RFBoost1 and AdaBoost.MH on all datasets. Finally, RFBoost1 proved more efficient than AdaBoost.MH, making it a better alternative for addressing classification problems in real-life applications and expert systems. [ABSTRACT FROM AUTHOR]

Abstract It is well established that natural aging negatively impacts on a wide variety of cognitive functions and research has sought to identify core neural mechanisms that may account for these disparate changes. A central feature of any cognitive task is the requirement to translate sensory information into an appropriate action - a process commonly known as perceptual decision making. While computational, psychophysical, and neurophysiological research has made substantial progress in establishing the key computations and neural mechanisms underpinning decision making, it is only relatively recently that this knowledge has begun to be applied to research on aging. The purpose of this review is to provide an overview of this work which is beginning to offer new insights into the core psychological processes that mediate age-related cognitive decline in adults aged 65 years and over. Mathematical modelling studies have consistently reported that older adults display longer non-decisional processing times and implement more conservative decision policies than their younger counterparts. However, there are limits on what we can learn from behavioural modeling alone and neurophysiological analyses can play an essential role in empirically validating model predictions and in pinpointing the precise neural mechanisms that are impacted by aging. Although few studies to date have explicitly examined correspondences between computational models and neural data with respect to cognitive aging, neurophysiological studies have already highlighted age-related changes at multiple levels of the sensorimotor hierarchy that are likely to be consequential for decision making behaviour. Here, we provide an overview of this literature and suggest some future directions for the field. [ABSTRACT FROM AUTHOR]

The threshold degree of a Boolean function f is the minimum degree of a real polynomial p that represents f in sign: f(x) = sgn p(x). Introduced in the seminal work of Minsky and Papert [Perceptrons: An Introduction to Computational Geometry, MIT Press, 1969], this notion is central to some of the strongest algorithmic and complexity-theoretic results for constant-depth circuits. One problem that has remained open for several decades, with applications to computational learning and communication complexity, is to determine the maximum threshold degree of a polynomial-size constant-depth circuit in n variables. The best lower bound prior to our work was Ω(n(d-1)/(2d-1)) for circuits of depth d. We obtain a polynomial improvement for every depth d; with a lower bound of Ω(n3/7) for depth 3 and Ω(pn) for depth d > 4: The proof contributes an approximation-theoretic technique of independent interest, which exploits asymmetry in circuits to prove their hardness for polynomials. [ABSTRACT FROM AUTHOR]

Computational Thinking (CT) is seen as an important competence that is required in order to adapt to the future. However, educators, especially K-12 teachers and researchers, have not clearly identified how to teach it. In this study, a meta-review of the studies published in academic journals from 2006 to 2017 was conducted to analyze application courses, adopted learning strategies, participants, teaching tools, programming languages, and course categories of CT education. From the review results, it was found that the promotion of CT in education has made great progress in the last decade. In addition to the increasing number of CT studies in different countries, the subjects, research issues, and teaching tools have also become more diverse in recent years. It was also found that CT has mainly been applied to the activities of program design and computer science, while some studies are related to other subjects. Meanwhile, most of the studies adopted Project-Based Learning, Problem-Based Learning, Cooperative Learning, and Game-based Learning in the CT activities. In other words, such activities as aesthetic experience, design-based learning, and storytelling have been relatively less frequently adopted. Most of the studies focused on programming skills training and mathematical computing, while some adopted a cross-domain teaching mode to enable students to manage and analyze materials of various domains by computing. In addition, since the cognitive ability of students of different ages varies, the CT ability cultivation methods and content criteria should vary accordingly. Moreover, most studies reported the learners' CT performance and perspectives, while their information society ability was seldom trained. Accordingly, the research trends and potential research issues of CT are proposed as a reference for researchers, instructors, and policy makers. [ABSTRACT FROM AUTHOR]

The threshold degree of a Boolean function f is the minimum degree of a real polynomial p that represents f in sign: f(x) ≡ sgn p(x). In a seminal 1969 monograph, Minsky and Papert constructed a polynomial-size constant-depth V; μg-circuit in n variables with threshold degree Ω(n1/3). This lower bound underlies some of today's strongest results on constant-depth circuits. It has since been an open problem [R. O'Donnell and R. A. Servedio: Proceedings of the 35th Annual ACM Symposium on Theory of Computing, 2003, pp. 325-334] to improve Minsky and Papert's bound to nΩ(1)+1/3. We give a detailed solution to this problem. For any fixed k ≤ 1; we construct an V; μg-formula of size n and depth k with threshold degree (nΩ(k-1)/(2k-1)). This lower bound nearly matches a known O(n) upper bound for arbitrary formulas and is exactly tight for\regular" formulas. Our result proves a conjecture due to O'Donnell and Servedio and a different conjecture due to [M. Bun and J. Thaler: Electronic Colloquium on Computational Complexity, Report TR13-151, 2013]. Applications to communication complexity and computational learning are given. [ABSTRACT FROM AUTHOR]

Abstract: This article presents a novel real‐time traffic network management system using an end‐to‐end deep learning (E2EDL) methodology. A computational learning model is trained, which allows the system to identify the time‐varying traffic congestion pattern in the network, and recommend integrated traffic management schemes to reduce this congestion. The proposed model structure captures the temporal and spatial congestion pattern correlations exhibited in the network, and associates these patterns with efficient traffic management schemes. The E2EDL traffic management system is trained using a laboratory‐generated data set consisting of pairings of prevailing traffic network conditions and efficient traffic management schemes designed to cope with these conditions. The system is applied for the US‐75 corridor in Dallas, Texas. Several experiments are conducted to examine the system performance under different traffic operational conditions. The results show that the E2EDL system achieves travel time savings comparable to those recorded for an optimization‐based traffic management system. [ABSTRACT FROM AUTHOR]

This paper models a warm standby system where a single element is online performing a specified mission task (e.g., a computing task) and subject to corrective replacement (CR) by an available standby element upon its failure. During the mission, preventive replacements (PRs) are also performed to renew the aged or worn online operating element before its actual failure according to a predetermined policy. In addition, to facilitate an effective restoration of system function in case of CR or PR happening, backups are also performed periodically so that the mission task can be resumed from the last successful backup point instead of from scratch. The mission succeeds if the specified mission task is accomplished; in other words, the mission fails when no operating elements remain prior to the mission task completion. In this paper, we make new contributions by first proposing an event transition-based numerical method to evaluate mission performance indices of the considered standby system subject to periodic backups, CR and PR. Mission success probability (MSP), expected mission completion time, expected mission operation cost (EMC), and expected uncompleted work fraction are evaluated. Based on the suggested evaluation algorithm, we make another contribution by formulating and solving optimization problems that help to determine the optimal backup-PR policy or the optimal combination of element activation sequencing and backup-PR policy to maximize MSP or minimize EMC. Influence of element performance and reliability parameters, data backup and retrieval complexity parameters on the optimal operation policy is investigated. Findings from this paper can guide the optimal decision making on policies related to element sequencing, backups as well as preventive maintenance planning, contributing toward reliable and cost-effective design and operation of standby computing systems. [ABSTRACT FROM AUTHOR]

With the advent of the fourth industrial revolution and the fast development of virtual/augmented reality, the number of high quality wireless services is exponentially increasing. This motivates the researchers to improve the system performance by integrating the limited wireless resources with some intelligent algorithms/schemes. We aim to explore intelligent/machine-learning algorithms for mobile communication networking systems. [Extracted from the article]

Multicasting is a useful network service in wireless mesh networks (WMNs) for delivering same data from a source to multiple destinations. An effective multicast routing protocol in multi-channel multi-radio WMNs (MCMR-WMNs) is required to satisfy the following criteria together: high network throughput, low end-to-end delay, low tree cost, low computational time, and load-aware routing. Furthermore, how to fully exploit channel diversity in MCMR-WMNs to accomplish low channel interference criteria is a critical issue in designing multicast routing protocol. In spite of its significance, multicast routing which satisfies all of the mentioned criteria, has not drawn much attention so far. Besides, major multicast routing protocols proposed in MCMR-WMNs are centralized or solve two problems of multicast tree construction and channel assignment sequentially. These protocols are time-consuming in addition to suffering from a single-point-of-failure. In this paper, we propose a distributed cross-layer algorithm for joint multicast routing and channel assignment in MCMR-WMNs. For the first time, we apply fuzzy credit assigned cerebellum model articulation controller (FCA-CMAC) neural network model to construct multicast routing tree considering load on the mesh nodes and the delay between neighboring mesh nodes. Moreover, we present a heuristic channel assignment algorithm aiming to reduce interference among the links of the multicast tree. FCA-CMAC converges quickly and creates minimal delay and load-aware multicast tree. Therefore, proposed method can optimize the network throughput, end-to-end delay, tree cost, and computational time. Additionally, channel assignment algorithm is subject to produce the minimal interference multicast tree. Simulation results show that in terms of aforementioned criteria, the proposed FCA-CMAC based multicast algorithm achieves better performance than those comparative references. [ABSTRACT FROM AUTHOR]

Online multi-object tracking aims at estimating the tracks of multiple objects instantly with each incoming frame and the information provided up to the moment. It still remains a difficult problem in complex scenes, because of the large ambiguity in associating multiple objects in consecutive frames and the low discriminability between objects appearances. In this paper, we propose a robust online multi-object tracking method that can handle these difficulties effectively. We first define the tracklet confidence using the detectability and continuity of a tracklet, and decompose a multi-object tracking problem into small subproblems based on the tracklet confidence. We then solve the online multi-object tracking problem by associating tracklets and detections in different ways according to their confidence values. Based on this strategy, tracklets sequentially grow with online-provided detections, and fragmented tracklets are linked up with others without any iterative and expensive association steps. For more reliable association between tracklets and detections, we also propose a deep appearance learning method to learn a discriminative appearance model from large training datasets, since the conventional appearance learning methods do not provide rich representation that can distinguish multiple objects with large appearance variations. In addition, we combine online transfer learning for improving appearance discriminability by adapting the pre-trained deep model during online tracking. Experiments with challenging public datasets show distinct performance improvement over other state-of-the-arts batch and online tracking methods, and prove the effect and usefulness of the proposed methods for online multi-object tracking. [ABSTRACT FROM AUTHOR]

Semi-supervised learning aims to utilize both labelled and unlabelled data to improve learning performance. This paper shows a distinct way to exploit unlabelled data for traditional semi-supervised learning methods, such as self-training. Self-training is a well-known semi-supervised learning algorithm which iteratively trains a classifier by bootstrapping from unlabelled data. Standard self-training barely selects unlabelled examples for training set augmentation according to the current classifier model, which is trained only on the labelled data. This could be problematic since the underlying classifier is not strong enough, especially when initial labelled data is sparse. Consequently, self-training suffers from too much classification noise accumulated in the training set. In this paper, we propose a novel self-training style algorithm, which exploits a manifold assumption to optimize the self-labelling process. Unlike standard self-training, our algorithm utilizes labelled and unlabelled data as a whole to label and select unlabelled examples for training set augmentation. In detail, two measures are employed to minimize the effect of noise introduced to the labelled training set: a transductive method based on controlled graph random walk is incorporated to generate reliable predictions on unlabelled data; secondly, the mechanism is adopted to sequentially augment the training set. Empirical results suggest that the proposed method can effectively improve classification performance. [ABSTRACT FROM AUTHOR]

Abstract: Humans excel in categorization. Yet from a computational standpoint, learning a novel probabilistic classification task involves severe computational challenges. The present paper investigates one way to address these challenges: assuming class‐conditional independence of features. This feature independence assumption simplifies the inference problem, allows for informed inferences about novel feature combinations, and performs robustly across different statistical environments. We designed a new Bayesian classification learning model (the dependence‐independence structure and category learning model, DISC‐LM) that incorporates varying degrees of prior belief in class‐conditional independence, learns whether or not independence holds, and adapts its behavior accordingly. Theoretical results from two simulation studies demonstrate that classification behavior can appear to start simple, yet adapt effectively to unexpected task structures. Two experiments—designed using optimal experimental design principles—were conducted with human learners. Classification decisions of the majority of participants were best accounted for by a version of the model with very high initial prior belief in class‐conditional independence, before adapting to the true environmental structure. Class‐conditional independence may be a strong and useful default assumption in category learning tasks. [ABSTRACT FROM AUTHOR]

A significant test for software is to task it with replicating human performance, as done recently with creative software and the commercial projectBeyond the Fence(undertaken for a television documentaryComputer Says Show). The remit of this project was to use computer software as much as possible to produce “the world's first computer-generated musical”. Several creative systems were used to generate this musical, which was performed in London's West End in 2016. This paper considers the challenge of evaluating this project. Current computational creativity evaluation methods are ill-suited to evaluating projects that involve creative input from multiple systems and people. Following recent inspiration within computational creativity research from interaction design, here the DECIDE evaluation framework is applied to evaluate theBeyond the Fenceproject. Evaluation finds that the project was reasonably successful at achieving the task of using computational generation to produce a credible musical. Lessons have been learned for future computational creativity projects though, particularly for affording creative software more agency and enabling software to interact with other creative partners. Upon reflection, the DECIDE framework emerges as a useful evaluation “checklist” (if not a tangible operational methodology) for evaluating multiple creative systems participating in a creative task. [ABSTRACT FROM PUBLISHER]