In the study of automatic summarization, the main research topic was `important sentence extraction' but nowadays `sentence compression' is a hot research topic. Conventional sentence compression methods usually transform a given sentence into a parse tree or a dependency tree, and modify them to get a shorter sentence. However, this method is sometimes too rigid. In this paper, we regard sentence compression as an combinatorial optimization problem that extracts an optimal subsequence of words. (...) Hori et al. also proposed a similar method, but they used only a small number of features and their weights were tuned by hand. We introduce a large number of features such as part-of-speech bigrams and word position in the sentence. Furthermore, we train the system by discriminative learning. According to our experiments, our method obtained better score than other methods with statistical significance. (shrink)

Using computer programs to correct English grammar can improve the efficiency of English grammar correction, improve the effect of error correction, and reduce the workload of manual error correction. In order to deal with and solve the problem of loss evaluation mismatch in the current mainstream machine translation, this study proposes the application of the deep learning method to propose an algorithm model with high error correction performance. Therefore, the framework of confrontation learning network is introduced to continuously improve the (...) optimization model parameters through the confrontation training of discriminator and generator. At the same time, convolutional neural network is introduced to improve the algorithm training effect, which can make the correction sentences generated by the model generator better in confrontation. In order to verify the performance of the algorithm model, P-value, R-value, F 0.5-value, and MRR-value were selected for the comprehensive evaluation of the model performance index. The simulation results of the CoNLL-2014 test set and Lang-8 test set show that the proposed algorithm model has significant performance improvement compared with the traditional transformer method and can correct the fluency of sentences. It has good application values. (shrink)

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data. Our efficiency is primarily due to the use of stochastic optimization techniques, as well as parallelization (...) and chart prefiltering. On WSJ15, we attain a state-of-the-art F-score of 90.9%, a 14% relative reduction in error over previous models, while being two orders of magnitude faster. On sentences of length 40, our system achieves an F-score of 89.0%, a 36% relative reduction in error over a generative baseline. (shrink)

In order to build high-quality concrete, it is imperative to know the raw materials in advance. It is possible to accurately predict the quality of concrete and the amount of raw materials used using machine learning-enhanced methods. An automated process based on machine learning strategies is proposed in this paper for predicting the compressive strength of concrete. Fusion-learning-based optimization is used in the proposed approach to generate a strong learner by pooling support vector regression models. The SVR technique proposes an (...) optimization method for finding the kernel radial basis function parameters based on improving the innovative gunner algorithm. As a result of AIG's diverse solutions, local optima are effectively avoided. Therefore, the novelty of our research is that, in solving the uncertainty of predicted outputs based on integrated models, we use fusion-learning-based optimization to improve regression discrimination. We also collected a standard dataset to analyze the proposed algorithm, and subsequently, the dataset was designed from concrete laboratory tests on 244 samples, seven features, and three outputs. Different regression intensities are determined by correlation analysis of responses. Regression fusion is sufficiently accurate to estimate the number of desired outcomes examined based on the appropriate input data sample. The best quality concrete can be achieved with an error rate of less than 5%. (shrink)

A considerable number of areas of bioscience, including gene and drug discovery, metabolic engineering for the biotechnological improvement of organisms, and the processes of natural and directed evolution, are best viewed in terms of a ‘landscape’ representing a large search space of possible solutions or experiments populated by a considerably smaller number of actual solutions that then emerge. This is what makes these problems ‘hard’, but as such these are to be seen as combinatorial optimisation problems that are best (...) attacked by heuristic methods known from that field. Such landscapes, which may also represent or include multiple objectives, are effectively modelled in silico, with modern active learning algorithms such as those based on Darwinian evolution providing guidance, using existing knowledge, as to what is the ‘best’ experiment to do next. An awareness, and the application, of these methods can thereby enhance the scientific discovery process considerably. This analysis fits comfortably with an emerging epistemology that sees scientific reasoning, the search for solutions, and scientific discovery as Bayesian processes. (shrink)

This book, first published in 1996, introduces students to optimization theory and its use in economics and allied disciplines. The first of its three parts examines the existence of solutions to optimization problems in Rn, and how these solutions may be identified. The second part explores how solutions to optimization problems change with changes in the underlying parameters, and the last part provides an extensive description of the fundamental principles of finite- and infinite-horizon dynamic programming. Each chapter contains (...) a number of detailed examples explaining both the theory and its applications for first-year master's and graduate students. 'Cookbook' procedures are accompanied by a discussion of when such methods are guaranteed to be successful, and, equally importantly, when they could fail. Each result in the main body of the text is also accompanied by a complete proof. A preliminary chapter and three appendices are designed to keep the book mathematically self-contained. (shrink)

Computational models of infant word‐finding typically operate over transcriptions of infant‐directed speech corpora. It is now possible to test models of word segmentation on speech materials, rather than transcriptions of speech. We propose that such modeling efforts be conducted over the speech of the experimental stimuli used in studies measuring infants' capacity for learning from spoken sentences. Correspondence with infant outcomes in such experiments is an appropriate benchmark for models of infants. We demonstrate such an analysis by applying the DP‐Parser (...) model of Algayres and colleagues to auditory stimuli used in infant psycholinguistic experiments by Pelucchi and colleagues. The DP‐Parser model takes speech as input, and creates multiple overlapping embeddings from each utterance. Prospective words are identified as clusters of similar embedded segments. This allows segmentation of each utterance into possible words, using a dynamic programming method that maximizes the frequency of constituent segments. We show that DP‐Parse mimics American English learners' performance in extracting words from Italian sentences, favoring the segmentation of words with high syllabic transitional probability. This kind of computational analysis over actual stimuli from infant experiments may be helpful in tuning future models to match human performance. (shrink)

A comprehensive introduction to optimization with a focus on practical algorithms for the design of engineering systems. This book offers a comprehensive introduction to optimization with a focus on practical algorithms. The book approaches optimization from an engineering perspective, where the objective is to design a system that optimizes a set of metrics subject to constraints. Readers will learn about computational approaches for a range of challenges, including searching high-dimensional spaces, handling problems where there are multiple competing objectives, and accommodating (...) uncertainty in the metrics. Figures, examples, and exercises convey the intuition behind the mathematical approaches. The text provides concrete implementations in the Julia programming language. Topics covered include derivatives and their generalization to multiple dimensions; local descent and first- and second-order methods that inform local descent; stochastic methods, which introduce randomness into the optimization process; linear constrained optimization, when both the objective function and the constraints are linear; surrogate models, probabilistic surrogate models, and using probabilistic surrogate models to guide optimization; optimization under uncertainty; uncertainty propagation; expression optimization; and multidisciplinary design optimization. Appendixes offer an introduction to the Julia language, test functions for evaluating algorithm performance, and mathematical concepts used in the derivation and analysis of the optimization methods discussed in the text. The book can be used by advanced undergraduates and graduate students in mathematics, statistics, computer science, any engineering field, (including electrical engineering and aerospace engineering), and operations research, and as a reference for professionals. (shrink)

Learning and Teaching in the Early Years provides a comprehensive, contemporary and practical introduction to early childhood teaching in Australia. A strong focus on the links between theory, policy and practice firmly aligns this text with the Early Years Learning Framework. Written for students of early childhood programs, this book covers learning and development, as well as professional practice in teaching children from birth to eight years. In recognition of the evolving role of educators, topic areas include learning, teaching, (...) working with families, leading, advocating and researching. Each chapter contains learning objectives, key terms and reflection points. Detailed case studies document the intersection between research, policy and practice, enhancing pre-service and practicing educators' appreciation of how a policy-aligned approach reinforces learning and development in the early years. This text draws on the latest research to present children's learning as a dynamic and active process requiring specific, intentional teaching behaviours. (shrink)

This chapter presents a new semantics for inductive empirical knowledge. The epistemic agent is represented concretely as a learner who processes new inputs through time and who forms new beliefs from those inputs by means of a concrete, computable learning program. The agent’s belief state is represented hyper-intensionally as a set of time-indexed sentences. Knowledge is interpreted as avoidance of error in the limit and as having converged to true belief from the present time onward. Familiar topics are re-examined within (...) the semantics, such as inductive skepticism, the logic of discovery, Duhem’s problem, the articulation of theories by auxiliary hypotheses, the role of serendipity in scientific knowledge, Fitch’s paradox, deductive closure of knowability, whether one can know inductively that one knows inductively, whether one can know inductively that one does not know inductively, and whether expert instruction can spread common inductive knowledge—as opposed to mere, true belief—through a community of gullible pupils. (shrink)

We present a general framework for analyzing the contribution to reproductive success of a behavioural action. An action may make a direct contribution to reproductive success, but even in the absence of a direct contribution it may make an indirect contribution by changing the animal's state. We consider actions over a period of time, and define a reward function that characterizes the relationship between the animal's state at the end of the period and its future reproductive success. Working back from (...) the end of the period using dynamic programming, the optimal action as a function of state and time can be found. The procedure also yields a measure of the cost, in terms of future reproductive success, of a suboptimal action. These costs provide us with a common currency for comparing activities such as eating and drinking, or eating and hiding from predators. The costs also give an indication of the robustness of the conclusions that can be drawn from a model. We review how our framework can be used to analyze optimal foraging decisions in a stochastic environment. We also discuss the modelling of optimal daily routines and provide an illustration based on singing to attract a mate. We use the model to investigate the features that can produce a dawn song burst in birds. State is defined very broadly so that it includes the information an animal has about its environment. Thus, exploration and learning can be included within the framework. (shrink)

The Language of First-Order Logic is a complete introduction to first-order symbolic logic, consisting of a computer program and a text. The program, an aid to learning and using symbolic notation, allows one to construct symbolic sentences and possible worlds, and verify that a sentence is well formed. The truth or falsity of a sentence can be determined by playing a deductive game with the computer.

The integration of machine learning algorithms into the legal recommendation system marks a burgeoning area of research, with a particular focus on enhancing the accuracy and efficiency of judicial decision-making processes. The application of Bayesian Network (BN) emerges as a potent tool in this context, promising to address the inherent complexities and unique nuances of legal texts and individual case subtleties. However, the challenge of achieving high accuracy in BN parameter learning, especially under conditions of limited data, remains a significant (...) hurdle. This study proposes an Enhanced Maximum Parameter Learning (EMPL) algorithm, tailored for BN parameter optimization in scenarios characterized by small sample sizes. The EMPL algorithm, innovatively incorporating the Synthetic Minority Over-sampling Technique (SMOTE), begins with the formulation of inequality constraints derived from domain expertise. It establishes a minimal dataset threshold necessary for effective parameter learning. Through the introduction of an index weighting factor function that dynamically adjusts according to the sample size, the algorithm facilitates the derivation of refined BN parameters. The core innovation of the EMPL algorithm lies in its use of an exponentially weighted factor function, designed to be responsive to variations in sample size, and its capacity to expand the parameter space using SMOTE to align with qualitative constraints from expert insights. This approach enables the integration of data-derived parameters with those obtained through expert experience in an exponentially weighted manner, culminating in the optimization of BN parameters. Comparative analysis reveals that the EMPL algorithm achieves superior learning accuracy over traditional Maximum Likelihood Estimation (MLE) and qualitative maximum a posteriori (QMAP) approach, particularly in contexts of sparse data. Furthermore, it demonstrates enhanced performance relative to variable weight learning algorithms, underscoring its potential to significantly improve decision-making processes in the legal domain through advanced BN parameter learning. (shrink)

Tarski's World 3.0 is an innovative and enjoyable way to introduce your students to the language of first-order logic. Using this program, students quickly master the meaning of the connectives and quantifiers, and soon become fluent in the symbolic language at the core of modern logic. Tarski's World allows the students to build three-dimensional worlds and describe them in first-order logic. They evaluate the sentences in the constructed worlds, and if their evaluation is incorrect, the program provides them with a (...) game that leads them to understand where they went wrong. The package is intended as a supplement to any standard logic text, or for use by anyone who wants to learn the language. The disk and manual contain over a hundred exercises from very basic to highly sophisticated. (shrink)

Job shop scheduling problem is one of the most difficult optimization problems in manufacturing industry, and flexible job shop scheduling problem is an extension of the classical JSP, which further challenges the algorithm performance. In FJSP, a machine should be selected for each process from a given set, which introduces another decision element within the job path, making FJSP be more difficult than traditional JSP. In this paper, a variant of grasshopper optimization algorithm named dynamic opposite learning assisted GOA (...) is proposed to solve FJSP. The recently proposed dynamic opposite learning strategy adopts the asymmetric search space to improve the exploitation ability of the algorithm and increase the possibility of finding the global optimum. Various popular benchmarks from CEC 2014 and FJSP are used to evaluate the performance of DOLGOA. Numerical results with comparisons of other classic algorithms show that DOLGOA gets obvious improvement for solving global optimization problems and is well-performed when solving FJSP. (shrink)

It is often thought that traditional recidivism prediction tools used in criminal sentencing, though biased in many ways, can straightforwardly avoid one particularly pernicious type of bias: direct racial discrimination. They can avoid this by excluding race from the list of variables employed to predict recidivism. A similar approach could be taken to the design of newer, machine learning-based (ML) tools for predicting recidivism: information about race could be withheld from the ML tool during its training phase, ensuring that the (...) resulting predictive model does not use race as an explicit predictor. However, if race is correlated with measured recidivism in the training data, the ML tool may ‘learn’ a perfect proxy for race. If such a proxy is found, the exclusion of race would do nothing to weaken the correlation between risk (mis)classifications and race. Is this a problem? We argue that, on some explanations of the wrongness of discrimination, it is. On these explanations, the use of an ML tool that perfectly proxies race would (likely) be more wrong than the use of a traditional tool that imperfectly proxies race. Indeed, on some views, use of a perfect proxy for race is plausibly as wrong as explicit racial profiling. We end by drawing out four implications of our arguments. (shrink)

This study examines the interplay between text summarization techniques and embeddings from Language Models (LMs) in constructing expert systems dedicated to the retrieval of legal precedents, with an emphasis on achieving cost-efficiency. Grounded in the growing domain of Artificial Intelligence (AI) in law, our research confronts the perennial challenges of computational resource optimization and the reliability of precedent identification. Through Named Entity Recognition (NER) and part-of-speech (POS) tagging, we juxtapose various summarization methods to distill legal documents into a convenient (...) form that retains their essence. We investigate the effectiveness of these methods in conjunction with state-of-the-art embeddings based on Large Language Models (LLMs), particularly ADA from OpenAI, which is trained on a wide range of general-purpose texts. Utilizing a dataset from one of Brazil’s administrative courts, we explore the efficacy of embeddings derived from a Transformer model tailored to legal corpora against those from ADA, gauging the impact of parameter size, training corpora, and context window on retrieving legal precedents. Our findings suggest that while the full text embedded with ADA’s extensive context window leads in retrieval performance, a balanced combination of POS-derived summaries and ADA embeddings presents a compelling trade-off between performance and resource expenditure, advocating for an efficient, scalable, intelligent system suitable for broad legal applications. This study contributes to the literature by delineating an optimal approach that harmonizes the dual imperatives of computational frugality and retrieval accuracy, propelling the legal field toward more strategic AI utilization. (shrink)

In this paper, we discuss a method to dynamically determine the generality of the target concept in a class hierarchy, when learning default rules, i.e., rules including exceptions with Inductive Logic Programming. The ILP system for default rules has to learn both the target concept and its opposite, if it is based on a three valued setting, in which we clearly discriminate among the three values: what is true, what is false, and what is unknown. Thus in order to (...) learn rules which holds as generally as possible in a class hierarchy implicitly existing in given examples, we should give a higher priority to the concept which is more general, or covers more examples than does the other in the hierarchy. For this purpose, our method first finds out the general rule from a set of candidate rules independently of the concept it defines. Then the body of the rule can be viewed as the description defining the most general class in the hierarchy. Therefore, according to the ratio of positive examples it covers, we can determine which of the concepts, the target one or its opposite, is more general, and dynamically change the head of the rule to the negative literal if the latter concept is more general. In this paper, we formalize this method as a new ILP system, GREX, and discuss it with some examples. (shrink)

Topic modelling is a popular unsupervised method for text processing that provides interpretable document representation. One of the most high-level approaches is additively regularized topic models (ARTM). This method features better quality than other methods due to its flexibility and advanced regularization abilities. However, it is challenging to find an optimal learning strategy to create high-quality topics because a user needs to select the regularizers with their values and determine the order of application. Moreover, it may require many real (...) runs or model training which makes this task time consuming. At the current moment, there is a lack of research on parameter optimization for ARTM-based models. Our work proposes an approach that formalizes the learning strategy into a vector of parameters which can be solved with evolutionary approach. We also propose a surrogate-based modification which utilizes machine learning methods that makes the approach for parameters search time efficient. We investigate different optimization algorithms (evolutionary and Bayesian) and their modifications with surrogates in application to topic modelling optimization using the proposed learning strategy approach. An experimental study conducted on English and Russian datasets indicates that the proposed approaches are able to find high-quality parameter solutions for ARTM and substantially reduce the execution time of the search. (shrink)

Experimentation is at the heart of scientific inquiry. In the behavioral and neural sciences, where only a limited number of observations can often be made, it is ideal to design an experiment that leads to the rapid accumulation of information about the phenomenon under study. Adaptive experimentation has the potential to accelerate scientific progress by maximizing inferential gain in such research settings. To date, most adaptive experiments have relied on myopic, one-step-ahead strategies in which the stimulus on each trial is (...) selected to maximize inference on the next trial only. A lingering question in the field has been how much additional benefit would be gained by optimizing beyond the next trial. A range of technical challenges has prevented this important question from being addressed adequately. This study applies dynamic programming, a technique applicable for such full-horizon, “global” optimization, to model-based perceptual threshold estimation, a domain that has been a major beneficiary of adaptive methods. The results provide insight into conditions that will benefit from optimizing beyond the next trial. Implications for the use of adaptive methods in cognitive science are discussed. (shrink)

Hyperproof is a system for learning the principles of analytical reasoning and proof construction, consisting of a text and a Macintosh software program. Unlike traditional treatments of first-order logic, Hyperproof combines graphical and sentential information, presenting a set of logical rules for integrating these different forms of information. This strategy allows students to focus on the information content of proofs, rather than the syntactic structure of sentences. Using Hyperproof the student learns to construct proofs of both consequence and nonconsequence (...) using an intuitive proof system that extends the standard set of sentential rules to incorporate information represented graphically. Hyperproof is compatible with various natural-deduction-style proof systems, including the system used in the authors' Language of First-Order Logic. (shrink)

Automatic text summarization extracts information from a source text and presents it to the user in a condensed form while preserving its primary content. Many text summarization approaches have been investigated in the literature for highly resourced languages. At the same time, ATS is a complicated and challenging task for under-resourced languages like Malayalam. The lack of a standard corpus and enough processing tools are challenges when it comes to language processing. In the absence of a standard (...) corpus, we have developed a dataset consisting of Malayalam news articles. This article proposes an extractive topic modeling-based multi-document text summarization approach for Malayalam news documents. We first cluster the contents based on latent topics identified using the latent Dirichlet allocation topic modeling technique. Then by adopting vector space model, the topic vector and sentence vector of the given document are generated. According to the relevant status value, sentences are ranked between the document’s topic and sentence vectors. The summary obtained is optimized for non-redundancy. Evaluation results on Malayalam news articles show that the summary generated by the proposed method is closer to the human-generated summaries than the existing text summarization methods. (shrink)

Proof and Consequence is a rigorous, elegant introduction to classical first-order natural deductive logic; it provides an accurate and accessible first course in the study of formal systems. The text covers all the topics necessary for learning logic at the beginner and intermediate levels: this includes propositional and quantificational logic (using Suppes-style proofs) and extensive metatheory, as well as over 800 exercises. Proof and Consequence provides exclusive access to the software application Simon, an easily downloadable program designed to facilitate (...) an intuitive understanding of classical logic through the generation and analysis of proofs. It also aids with the representation of natural language sentences in the formal language. Equipped with nearly all the exercises found in the text, Simon helps students work efficiently and effectively by detecting and explaining errors in solutions as they proceed. Students can also submit assignments, view their own records, and check their standing in the class. The complete logic package includes: * The logic textbook, Proof and Consequence *A very helpful study guide to the textbook, containing extra exercises, Simple Simon *Access, through Simon, to the grading software, Simon Says, that allows students to submit assignments and track their grades. (shrink)

A neural network is a model of the brain’s cognitive process, with a highly interconnected multiprocessor architecture. The neural network has incredible potential, in the view of these artificial neural networks inherently having good learning capabilities and the ability to learn different input features. Based on this, this paper proposes a new chaotic neuron model and a new chaotic neural network model. It includes a linear matrix, a sine function, and a chaotic neural network composed of three chaotic neurons. One (...) of the chaotic neurons is affected by the sine function. The network has rich chaotic dynamics and can produce multiscroll hidden chaotic attractors. This paper studied its dynamic behaviors, including bifurcation behavior, Lyapunov exponent, Poincaré surface of section, and basins of attraction. In the process of analyzing the bifurcation and the basins of attraction, it was found that the network demonstrated hidden bifurcation phenomena, and the relevant properties of the basins of attraction were obtained. Thereafter, a chaotic neural network was implemented by using FPGA, and the experiment proved that the theoretical analysis results and FPGA implementation were consistent with each other. Finally, an energy function was constructed to optimize the calculation based on the CNN in order to provide a new approach to solve the TSP problem. (shrink)

A pioneering look at the fundamental role of logic in optimizationand constraint satisfaction While recent efforts to combine optimization and constraintsatisfaction have received considerable attention, little has beensaid about using logic in optimization as the key to unifying thetwo fields. Logic-Based Methods for Optimization develops for thefirst time a comprehensive conceptual framework for integratingoptimization and constraint satisfaction, then goes a step furtherand shows how extending logical inference to optimization allowsfor more powerful as well as flexible modeling and solutiontechniques. Designed to (...) be easily accessible to industryprofessionals and academics in both operations research andartificial intelligence, the book provides a wealth of examples aswell as elegant techniques and modeling frameworks ready forimplementation. Timely, original, and thought-provoking,Logic-Based Methods for Optimization: * Demonstrates the advantages of combining the techniques inproblem solving * Offers tutorials in constraint satisfaction/constraintprogramming and logical inference * Clearly explains such concepts as relaxation, cutting planes,nonserial dynamic programming, and Bender's decomposition * Reviews the necessary technologies for software developersseeking to combine the two techniques * Features extensive references to important computationalstudies * And much more. (shrink)

One of the problems when students go to university is that they are faced with insufficient skills (reading, summarizing and writing). These skills are not just an option for students – they are a necessity. One of these skills is text summarizing. Summarizing strategies may be called the gist of the literary text. Different summarization strategies may be required for different text types and lengths. The ability to summarize well means your reading comprehension and writing skill should (...) be excellent. Summarization is a high-level comprehension strategy which is effective in improving reading achievement and text summary quality.Several approaches have been developed to analyse summarizing skills which are required to teach and learn English at all levels especially at university level. The research was conducted among students of the second year English department at University of Vlora. The summaries reflect the major differences among the strategies used by skilled and unskilled students. The skilled students produce coherent linguistic and syntactic structures. Skilled (high-proficiency) students use semantic and prepositional phrases more than unskilled students (low-proficiency). Thus, the skilled students do not distort ideas of the original text but distort subject-verb order. When they summarize, we can easily distinguish the way in which they combine idea units across two or more paragraphs. The summaries reflect that students write very long sentences. The margin of errors is considerable due to the mother tongue influence and their level of English. (shrink)

We want to highlight the strong link between learning systems such as deep learning neural networks and neutrosophy. The latter is above all a representation considering a neutral state which is at the heart of many phenomena of reality as well as mathematical and information theories. Here, we start from the recent understanding of neural networks, which considers their internal functioning and the learning that characterizes them as based on adapted representations (both of the information to be processed and of (...) the task to be performed) that are in fact optimal compressions. Compression means discriminating the similar and the different between cases by identifying representative characteristics through focusing on the most significant and rejecting of the rest. These three operations of neural processing, learning and compression owe their existence to non-linear treatments which essentially amount to distinguishing a neutral zone between two filtered zones, corresponding to the neutrosophical approach. (shrink)

Human cognition is unique in the way in which it relies on combinatorial (or compositional) structures. Language provides ample evidence for the existence of combinatorial structures, but they can also be found in visual cognition. To understand the neural basis of human cognition, it is therefore essential to understand how combinatorial structures can be instantiated in neural terms. In his recent book on the foundations of language, Jackendoff described four fundamental problems for a neural instantiation of (...) class='Hi'>combinatorial structures: the massiveness of the binding problem, the problem of 2, the problem of variables, and the transformation of combinatorial structures from working memory to long-term memory. This paper aims to show that these problems can be solved by means of neural “blackboard” architectures. For this purpose, a neural blackboard architecture for sentence structure is presented. In this architecture, neural structures that encode for words are temporarily bound in a manner that preserves the structure of the sentence. It is shown that the architecture solves the four problems presented by Jackendoff. The ability of the architecture to instantiate sentence structures is illustrated with examples of sentence complexity observed in human language performance. Similarities exist between the architecture for sentence structure and blackboard architectures for combinatorial structures in visual cognition, derived from the structure of the visual cortex. These architectures are briefly discussed, together with an example of a combinatorial structure in which the blackboard architectures for language and vision are combined. In this way, the architecture for language is grounded in perception. Perspectives and potential developments of the architectures are discussed. Key Words: binding; blackboard architectures; combinatorial structure; compositionality; language; dynamic system; neurocognition; sentence complexity; sentence structure; working memory; variables; vision. (shrink)

We present a general theory of scope and binding in which both crossover and superiority violations are ruled out by one key assumption: that natural language expressions are normally evaluated (processed) from left to right. Our theory is an extension of Shan’s (2002) account of multiple-wh questions, combining continuations (Barker, 2002) and dynamic type-shifting. Like other continuation-based analyses, but unlike most other treatments of crossover or superiority, our analysis is directly compositional (in the sense of, e.g., Jacobson, 1999). In (...) particular, it does not postulate a level of Logical Form or any other representation distinct from surface syntax. One advantage of using continuations is that they are the standard tool for modeling order-of-evaluation in programming languages. This provides us with a natural and independently motivated characterization of what it means to evaluate expressions from left to right. We give a combinatory categorial grammar that models the syntax and the semantics of quantifier scope and wh-question formation. It allows quantificational binding but not crossover, in-situ wh but not superiority violations. In addition, the analysis automatically accounts for a variety of sentence types involving binding in the presence of pied piping, including reconstruction cases such as Whose criticism of hisi mother did each personi resent? (shrink)

Tetris provides a difficult, dynamic task environment within which some people are novices and others, after years of work and practice, become extreme experts. Here we study two core skills; namely, choosing the goal or objective function that will maximize performance and a feature-based analysis of the current game board to determine where to place the currently falling zoid so as to maximize the goal. In Study 1, we build cross-entropy reinforcement learning models to determine whether different goals result (...) in different feature weights. Two of these optimization strategies quickly rise to performance plateaus, whereas two others continue toward higher but more jagged heights. In Study 2, we compare the zoid placement decisions made by our best CERL models with those made by 67 human players. Across 370,131 human game episodes, two CERL models picked the same zoid placements as our lowest scoring human for 43% of the placements and as our three best scoring experts for 65% of the placements. Our findings suggest that people focus on maximizing points, not number of lines cleared or number of levels reached. They also show that goal choice influences the choice of zoid placements for CERLs and suggest that the same is true of humans. Tetris has a repetitive task structure that makes Tetris more tractable and more like a traditional experimental psychology paradigm than many more complex games or tasks. Hence, although complex, Tetris is not overwhelmingly complex and presents a right-sized challenge to cognitive theories, especially those of integrated cognitive systems. (shrink)

Two aspects of dynamic systems approaches that are pertinent to developmental models of reading are the emergence of a system with self-organizing characteristics, and its evolution over time to a stable state that is not easily modified or perturbed. The effects of dynamic stability may be seen in the differences obtained in the processing of print by beginner readers taught by different approaches to reading (phonics and text-centered), and more long-term effects on adults, consistent with these differences. (...) However, there is little direct evidence collected over time for the same participants. In this study, lexicalized (implicit) phonological processing, and explicit phonological and letter-sound skills are further examined in a precocious reader whose early development at 3 and 5 years has been extensively described (Cognition, 2000, 2004). At ages 10 and 14 years, comparisons were made with these earlier reports and skilled adult readers, using the same tasks for evidence of changes in reading processes. The results showed that along with an increase of reading accuracy and speed, her pattern of lexicalized phonological responses for reading did not change over time. Neither did her pattern of explicit phonological and letter-sound skills, aspects of which were inferior to her lexicalized phonological processing, and word reading. These results suggest dynamic stability of the word reading system. The early emergence of this system with minimal explicit skill development calls into question developmental reading theories that require such skills for learning to read. Currently, only the Knowledge Sources theory of reading acquisition can account for such findings. Consideration of these aspects of dynamic systems raise theoretical issues that could result in a paradigm shift with regard to best practice and intervention. (shrink)

We apply an online optimization process based on machine learning to the production of Bose-Einstein condensates. BEC is typically created with an exponential evaporation ramp that is optimal for ergodic dynamics with two-body s-wave interactions and no other loss rates, but likely sub-optimal for real experiments. Through repeated machine-controlled scientific experimentation and observations our ’learner’ discovers an optimal evaporation ramp for BEC production. In contrast to previous work, our learner uses a Gaussian process to develop a statistical model of the (...) relationship between the parameters it controls and the quality of the BEC produced. We demonstrate that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique. Furthermore, we show the internal model developed can be used to determine which parameters are essential in BEC creation and which are unimportant, providing insight into the optimization process of the system. (shrink)

Sentence boundary detection (SBD) represents an important first step in natural language processing since accurately identifying sentence boundaries significantly impacts downstream applications. Nevertheless, detecting sentence boundaries within legal texts poses a unique and challenging problem due to their distinct structural and linguistic features. Our approach utilizes deep learning models to leverage delimiter and surrounding context information as input, enabling precise detection of sentence boundaries in English legal texts. We evaluate various deep learning models, including domain-specific transformer (...) models like LegalBERT and CaseLawBERT. To assess the efficacy of our deep learning models, we compare them with a state-of-the-art domain-specific statistical conditional random field (CRF) model. After considering model size, F1-score, and inference time, we identify the Convolutional Neural Network Model (CNN) as the top-performing deep learning model. To further enhance performance, we integrate the features of the CNN model into the subsequent CRF model, creating a hybrid architecture that combines the strengths of both models. Our experiments demonstrate that the hybrid model outperforms the baseline model, achieving a 4% improvement in the F1-score. Additional experiments showcase the superiority of the hybrid model over SBD open-source libraries when confronted with an out-of-domain test set. These findings underscore the importance of efficient SBD in legal texts and emphasize the advantages of employing deep learning models and hybrid architectures to achieve optimal performance. (shrink)

Programming artificial intelligence to make fairness assessments of texts through top-down rules, bottom-up training, or hybrid approaches, has presented the challenge of defining cross-cultural fairness. In this paper a simple method is presented which uses vectors to discover if a verb is unfair or fair. It uses already existing relational social ontologies inherent in Word Embeddings and thus requires no training. The plausibility of the approach rests on two premises. That individuals consider fair acts those that they would be (...) willing to accept if done to themselves. Secondly, that such a construal is ontologically reflected in Word Embeddings, by virtue of their ability to reflect the dimensions of such a perception. These dimensions being: responsibility vs. irresponsibility, gain vs. loss, reward vs. sanction, joy vs. pain, all as a single vector. The paper finds it possible to quantify and qualify a verb as fair or unfair by calculating the cosine similarity of the said verb’s embedding vector against FairVec—which represents the above dimensions. We apply this to Glove and Word2Vec embeddings. Testing on a list of verbs produces an F1 score of 95.7, which is improved to 97.0. Lastly, a demonstration of the method’s applicability to sentence measurement is carried out. (shrink)

Because of the difficulty of music feature recognition due to the complex and varied music theory knowledge influenced by music specialization, we designed a music feature recognition system based on Internet of Things technology. The physical sensing layer of the system places sound sensors at different locations to collect the original music signals and uses a digital signal processor to carry out music signal analysis and processing. The network transmission layer transmits the completed music signals to the music signal database (...) in the application layer of the system. The music feature analysis module of the application layer uses a dynamic time regularization algorithm to obtain the maximum similarity between the test template and the reference. The music feature analysis module of the application layer uses the dynamic time regularization algorithm to obtain the maximum similarity between the test template and the reference template to realize the feature recognition of the music signal and determine the music pattern and music emotion corresponding to the music feature content according to the recognition result. The experimental results show that the system operates stably, can capture high-quality music signals, and can correctly identify music style features and emotion features. The results of this study can meet the needs of composers’ assisted creation and music researchers’ analysis of a large amount of music data, and the results can be further transferred to deep music learning research, human-computer interaction music creation, application-based music creation, and other fields for expansion. (shrink)

Because of the lack of interaction between seeking mode cats and tracking mode cats in cat swarm optimization, its convergence speed and convergence accuracy are affected. An information interaction strategy is designed between seeking mode cats and tracking mode cats to improve the convergence speed of the CSO. To increase the diversity of each cat, a top-N learning strategy is proposed during the tracking process of tracking mode cats to improve the convergence accuracy of the CSO. On ten standard test (...) functions, the average values, standard deviations, and optimal values of the proposed algorithm with different N values are compared with the original CSO algorithm and the adaptive cat swarm algorithm based on dynamic search. Experimental results show that the global search ability and the convergence speed of the proposed algorithm are significantly improved on all test functions. The proposed two strategies will improve the convergence accuracy and convergence speed of CSO greatly. (shrink)

This volume-"Selected Contemporary Challenges of Aging Policy"-is the most international of all published monographs from the series "Czech-Polish-Slovak Studies in Andragogy and Social Gerontology." Among the scholars trying to grasp the nuances and trends of social policy, there are diverse perspectives, resulting not only from the extensive knowledge of the authors on the systematic approach to the issue of supporting older people but also from the grounds of the represented social gerontology schools. In the texts of Volume VII interesting are (...) both distinct and coherent elements presenting the role of local, regional and global policies in the prism of the countries from which the authors originate: the Czech Republic, Slovenia, Lithuania, Latvia, Poland, Slovakia, Italy, Turkey, and the United States. The chapters show a wealth of methodological approaches to the perception of social policy and its tools. In the texts there are issues related to the idea of active ageing, discrimination against older people in the workplace, comparability of solutions friendly to employment of older adults in the Czech Republic, Poland, and Slovakia as well as focused on the importance of educational forms determining an active life in old age. This monograph also attempted to answer the question regarding how to transfer the idea of intergenerational learning into the realm of practice. This issue complements the chapter on the implementation of intergenerational programs in institutions providing long-term care support. The book also outlines a public policy on ageing in the perspective of the changes over the last few decades and the case demonstrating solutions to accelerate self-reliance as a key to active ageing. We hope that seventh volume of our series will be an intellectual stimulus for further international research on change in social policy and will contribute to the dissemination of best practices as well as contribute to positive social change. (shrink)

This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set of 2550 EEG statistical features. Optimisation of a Multilayer Perceptron is performed with an evolutionary approach before classification to estimate the best hyperparameters of the network. Deep learning and tuning with Long (...) Short-Term Memory are also explored, and Adaptive Boosting of the two types of models is tested for each problem. Three experiments are provided for comparison using different classifiers: one for attention state classification, one for emotional sentiment classification, and a third experiment in which the goal is to guess the number a subject is thinking of. The obtained results show that an Adaptive Boosted LSTM can achieve an accuracy of 84.44%, 97.06%, and 9.94% on the attentional, emotional, and number datasets, respectively. An evolutionary-optimised MLP achieves results close to the Adaptive Boosted LSTM for the two first experiments and significantly higher for the number-guessing experiment with an Adaptive Boosted DEvo MLP reaching 31.35%, while being significantly quicker to train and classify. In particular, the accuracy of the nonboosted DEvo MLP was of 79.81%, 96.11%, and 27.07% in the same benchmarks. Two datasets for the experiments were gathered using a Muse EEG headband with four electrodes corresponding to TP9, AF7, AF8, and TP10 locations of the international EEG placement standard. The EEG MindBigData digits dataset was gathered from the TP9, FP1, FP2, and TP10 locations. (shrink)

Merging logic and mathematics in deductive inference-an innovative, cutting-edge approach. Optimization methods for logical inference? Absolutely, say Vijay Chandru and John Hooker, two major contributors to this rapidly expanding field. And even though "solving logical inference problems with optimization methods may seem a bit like eating sauerkraut with chopsticks... it is the mathematical structure of a problem that determines whether an optimization model can help solve it, not the context in which the problem occurs." Presenting powerful, proven optimization techniques for (...) logic inference problems, Chandru and Hooker show how optimization models can be used not only to solve problems in artificial intelligence and mathematical programming, but also have tremendous application in complex systems in general. They survey most of the recent research from the past decade in logic/optimization interfaces, incorporate some of their own results, and emphasize the types of logic most receptive to optimization methods-propositional logic, first order predicate logic, probabilistic and related logics, logics that combine evidence such as Dempster-Shafer theory, rule systems with confidence factors, and constraint logic programming systems. Requiring no background in logic and clearly explaining all topics from the ground up, Optimization Methods for Logical Inference is an invaluable guide for scientists and students in diverse fields, including operations research, computer science, artificial intelligence, decision support systems, and engineering. (shrink)

The current study examined whether pigeons could learn to use abstract concepts as the basis for conditionally switching behavior as a function of time. Using a mid-session reversal task, experienced pigeons were trained to switch from matching-to-sample (MTS) to non-matching-to-sample (NMTS) conditional discriminations within a session. One group had prior training with MTS, while the other had prior training with NMTS. Over training, stimulus set size was progressively doubled from 3 to 6 to 12 stimuli to promote abstract concept development. (...) Prior experience had an effect on the initial learning at each of the set sizes but by the end of training there were no group differences, as both groups showed similar within-session linear matching functions. After acquiring the 12-item set, abstract-concept learning was tested by placing novel stimuli at the beginning and end of a test session. Prior matching and non-matching experience affected transfer behavior. The matching experienced group transferred to novel stimuli in both the matching and non-matching portion of the sessions using a matching rule. The non-matching experienced group transferred to novel stimuli in both portions of the session using a non-matching rule. The representations used as the basis for mid-session reversal of the conditional discrimination behaviors and subsequent transfer behavior appears to have different temporal sources. The implications for the flexibility and organization of complex behaviors are considered. (shrink)

A large number of modern communication technologies and sensing technologies are incorporated into the smart grid, which makes its structure unique. The centralized optimized dispatch method of traditional power grids is difficult to achieve effective dispatch of smart grids. Based on the analysis of power generation plan and maintenance plan optimization model, this paper establishes a smart grid power generation and maintenance collaborative optimization model with distributed renewable energy. The objective function of this collaborative optimization problem is the operating cost (...) of conventional units, the cost of wind power generation, and the cost of overhauling units; the constraints considered mainly include system constraints and overhaul constraints. The solution method of combinatorial optimization is analyzed, and the genetic optimization algorithm adopted in this paper is selected and discussed. According to the characteristics of the system, various loads are modeled, and power supply constraints are considered. By establishing an effective objective function, the adjustable load scheduling problem is transformed into a solvable optimal control problem. Taking into account the uncertain factors in the system, the advantage of the real-time control system is that it can realize the dynamic update scheduling of the load, so it is more in line with the requirements of the actual system. The real-time algorithm proposed in the paper is based on a distributed control strategy, which can not only realize dynamic compensation for random fluctuations in renewable energy power generation but also satisfy the load curve optimization under the premise of making full use of power supply resources. In addition, simulation experiments compare the load dispatching capabilities of the proposed algorithm with the existing algorithms, thereby verifying the performance of the proposed method. (shrink)

This paper is concerned with autonomous learning of plans in probabilistic domains without a priori domain-specific knowledge. In contrast to existing reinforcement learning algorithms that generate only reactive plans and existing probabilistic planning algorithms that require a substantial amount of a priori knowledge in order to plan, a two-stage bottom-up process is devised, in which first reinforcement learning/dynamic programming is applied, without the use of a priori domain-specific knowledge, to acquire a reactive plan and then explicit plans are (...) extracted from the reactive plan. Several options for plan extraction are examined, each of which is based on a beam search that performs temporal projection in a restricted fashion, guided by the value functions resulting from reinforcement learning/dynamic programming. Some completeness and soundness results are given. Examples in several domains are discussed that together demonstrate the working of the proposed model. (shrink)

Di erent from existing reinforcement learning algorithms that generate only reactive policies and existing probabilis tic planning algorithms that requires a substantial amount of a priori knowledge in order to plan we devise a two stage bottom up learning to plan process in which rst reinforce ment learning dynamic programming is applied without the use of a priori domain speci c knowledge to acquire a reactive policy and then explicit plans are extracted from the learned reactive policy Plan (...) extraction is based on a beam search algorithm that performs temporal projection in a restricted fashion guided by the value functions re sulting from reinforcement learning dynamic programming Experiments and theoretical analysis are presented.. (shrink)