1. Introduction 2. Reward-Guided Decision Making 3. Content in the Model 4. How to Deflate a Metarepresentational Reading Proust and Carruthers on metacognitive feelings 5. A Deflationary Treatment of RPEs? 5.1 Dispensing with prediction errors 5.2 What is use of the RPE focused on? 5.3 Alternative explanations—worldly correlates 5.4 Contrast cases 6. Conclusion Appendix: Temporal Difference Learning Algorithms.

This paper considers the consensus control problem of nonlinear spatial-temporal hyperbolic partial difference multiagent systems and parabolic partial difference multiagent systems with time delay. Based on the system’s own fixed topology and the method of generating the desired trajectory by introducing virtual leader, using the consensus tracking error between the agent and the virtual leader agent and neighbor agents in the last iteration, an iterative learning algorithm is proposed. The sufficient condition for the system consensus (...) error to converge along the iterative axis is given. When the iterative learning number k approaches infinity, the consensus error in the sense of the L 2 norm between all agents in the system will converge to zero. Furthermore, simulation results illustrate the effectiveness of the algorithm. (shrink)

In reinforcement learning, a decision maker searching for the most rewarding option is often faced with the question: What is the value of an option that has never been tried before? One way to frame this question is as an inductive problem: How can I generalize my previous experience with one set of options to a novel option? We show how hierarchical Bayesian inference can be used to solve this problem, and we describe an equivalence between the Bayesian model (...) and temporal difference learning algorithms that have been proposed as models of RL in humans and animals. According to our view, the search for the best option is guided by abstract knowledge about the relationships between different options in an environment, resulting in greater search efficiency compared to traditional RL algorithms previously applied to human cognition. In two behavioral experiments, we test several predictions of our model, providing evidence that humans learn and exploit structured inductive knowledge to make predictions about novel options. In light of this model, we suggest a new interpretation of dopaminergic responses to novelty. (shrink)

This article recapitulates and develops the attempts in the Nietzschean traditions to address and overcome the proliferation of nihilism that Nietzsche predicted to unfold in the next 200 years (WP 2). Nietzsche approached nihilism not merely as a psychology but as a labyrinthic and pervasive historical process whereby the highest values of culture and founding assumptions of philosophical thought prevented the further flourishing of life. Therefore, he thought nihilism had to be encountered and experienced on many, often opposing, fronts to (...) be fully consumed and left behind. Thus, just as Nietzsche captured the subtle reinventions of nihilism in new forms in his time, in the new doers assumed behind new deeds (WP 488), this article focuses on the contemporary tectonic shifts brought by digital technology and challenges subjectivation and narrativization of algorithmic will to power in human-like interfaces such as ChatGPT. Having identified philosophers and himself as the most advanced nihilists in their overvaluation of truth, in the 4th part of Thus Spoke Zarathustra, Nietzsche grappled with the difficult, perhaps impossible, temporality of post-nihilistic historicity that oscillates between highest creativity and highest truths, especially in the sections entitled The Shadow and At Noon whereby he explored new temporal techniques to evade the relapses into temporal nihilisms of the notions of linear progress or eternity (TSZ, 4). By drawing on this juncture, this article offers ways to address transfigurations of nihilism behind new technological performances of subjectivity. The article points toward creative temporalities beyond narrativity and subjectivity insofar as the statistical operations and probabilistic estimations of language-models exceed grammatical construction of meaning. This multifaceted application of his thought on the contemporary ontic reality is necessary to perceive our comet's incalculable movement as a veritable ray of sunshine. (shrink)

A new model of the development of temporal concepts is described that assumes that there are substantial changes in how children think about time in the early years. It is argued that there is a shift from understanding time in an event-dependent way to an event-independent understanding of time. Early in development, very young children are unable to think about locations in time independently of the events that occur at those locations. It is only with development that children begin (...) to have a proper grasp of the distinction between past, present, and future, and represent time as linear and unidirectional. The model assumes that although children aged 2 to 3 years may categorize events differently depending on whether they lie in the past or the future, they may not be able to understand that whether an event is in the past or future is something that changes as time passes and varies with temporal perspective. Around 4 to 5 years, children understand how causality operates in time, and can grasp the systematic relations that obtain between different locations in time, which provides the basis for acquiring the conventional clock and calendar system. (shrink)

The fields of machine learning (ML) and cognitive science have developed complementary approaches to computationally modeling human behavior. ML's primary concern is maximizing prediction accuracy; cognitive science's primary concern is explaining the underlying mechanisms. Cross-talk between these disciplines is limited, likely because the tasks and goals usually differ. The domain of e-learning and knowledge acquisition constitutes a fruitful intersection for the two fields’ methodologies to be integrated because accurately tracking learning and forgetting over time and predicting future (...) performance based on learning histories are central to developing effective, personalized learning tools. Here, we show how a state-of-the-art ML model can be enhanced by incorporating insights from a cognitive model of human memory. This was done by exploiting the predictive performance equation's (PPE) narrow but highly specialized domain knowledge with regard to the temporal dynamics of learning and forgetting. Specifically, the PPE was used to engineer timing-related input features for a gradient-boosted decision trees (GBDT) model. The resulting PPE-enhanced GBDT outperformed the default GBDT, especially under conditions in which limited data were available for training. Results suggest that integrating cognitive and ML models could be particularly productive if the available data are too high-dimensional to be explained by a cognitive model but not sufficiently large to effectively train a modern ML algorithm. Here, the cognitive model's insights pertaining to only one aspect of the data were enough to jump-start the ML model's ability to make predictions—a finding that holds promise for future explorations. (shrink)

The fields of machine learning (ML) and cognitive science have developed complementary approaches to computationally modeling human behavior. ML's primary concern is maximizing prediction accuracy; cognitive science's primary concern is explaining the underlying mechanisms. Cross-talk between these disciplines is limited, likely because the tasks and goals usually differ. The domain of e-learning and knowledge acquisition constitutes a fruitful intersection for the two fields’ methodologies to be integrated because accurately tracking learning and forgetting over time and predicting future (...) performance based on learning histories are central to developing effective, personalized learning tools. Here, we show how a state-of-the-art ML model can be enhanced by incorporating insights from a cognitive model of human memory. This was done by exploiting the predictive performance equation's (PPE) narrow but highly specialized domain knowledge with regard to the temporal dynamics of learning and forgetting. Specifically, the PPE was used to engineer timing-related input features for a gradient-boosted decision trees (GBDT) model. The resulting PPE-enhanced GBDT outperformed the default GBDT, especially under conditions in which limited data were available for training. Results suggest that integrating cognitive and ML models could be particularly productive if the available data are too high-dimensional to be explained by a cognitive model but not sufficiently large to effectively train a modern ML algorithm. Here, the cognitive model's insights pertaining to only one aspect of the data were enough to jump-start the ML model's ability to make predictions—a finding that holds promise for future explorations. (shrink)

Social bots are computer programs that act like human users on social media platforms. Social bot detection is a rapidly growing field dominated by machine learning approaches. In this paper, we propose a complementary method to machine learning by exploring bot detection as a model checking problem. We introduce Temporal Network Logic (TNL) which we use to specify social networks where agents can post and follow each other. Using this logic, we formalize different types of social bot (...) behavior with formulas that are satisfied in a model of a network with bots. We also consider an extension of the logic where we explore the expressive power of including elements from hybrid logic in our framework. We give model checking algorithms for TNL and its hybrid extension, and show that the complexity of the former is in p and the latter in pspace. (shrink)

Floods are one of the most common natural disasters in the world that affect all aspects of life, including human beings, agriculture, industry, and education. Research for developing models of flood predictions has been ongoing for the past few years. These models are proposed and built-in proportion for risk reduction, policy proposition, loss of human lives, and property damages associated with floods. However, flood status prediction is a complex process and demands extensive analyses on the factors leading to the occurrence (...) of flooding. Consequently, this research proposes an Internet of Things-based flood status prediction (IoT-FSP) model that is used to facilitate the prediction of the rivers flood situation. The IoT-FSP model applies the Internet of Things architecture to facilitate the flood data acquisition process and three machine learning (ML) algorithms, which are Decision Tree (DT), Decision Jungle, and Random Forest, for the flood prediction process. The IoT-FSP model is implemented in MATLAB and Simulink as development platforms. The results show that the IoT-FSP model successfully performs the data acquisition and prediction tasks and achieves an average accuracy of 85.72% for the three-fold cross-validation results. The research finding shows that the DT scores the highest accuracy of 93.22%, precision of 92.85, and recall of 92.81 among the three ML algorithms. The ability of the ML algorithm to handle multivariate outputs of 13 different flood textual statuses provides the means of manifesting explainable artificial intelligence and enables the IoT-FSP model to act as an early warning and flood monitoring system. (shrink)

The accurate recognition of speech is beneficial to the fields of machine translation and intelligent human–computer interaction. After briefly introducing speech recognition algorithms, this study proposed to recognize speech with a recurrent neural network (RNN) and adopted the connectionist temporal classification (CTC) algorithm to align input speech sequences and output text sequences forcibly. Simulation experiments compared the RNN-CTC algorithm with the Gaussian mixture model–hidden Markov model and convolutional neural network-CTC algorithms. The results demonstrated that the more training (...) samples the speech recognition algorithm had, the higher the recognition accuracy of the trained algorithm was, but the training time consumption increased gradually; the more samples a trained speech recognition algorithm had to test, the lower the recognition accuracy and the longer the testing time. The proposed RNN-CTC speech recognition algorithm always had the highest accuracy and the lowest training and testing time among the three algorithms when the number of training and testing samples was the same. (shrink)

Upshot: We acknowledge that our model can be implemented with different reinforcement learning algorithms. Subsystem formation has been successfully demonstrated on the basal level, and in order to show full subsystem formation in the communication system at least both intentional utterances and acceptance/rejection need to be implemented. The comments about intrinsic vs extrinsic rewards made clear that this distinction is not helpful in the context of the constructivist paradigm but rather needs to be replaced by a critical reflection on (...) whether one has truly created autopoietic agents or just an engineering system. (shrink)

With the development of computer hardware and software, digital art is a new discipline. It uses computers and digital technology as tools to perform artistic expression. It can be expanded to various binary numerical codes with computers as the center and can also be refined to various categories of creation with computers. The research scope is set in the field of digital art, and all kinds of accidental factors of digital art creation based on the machine learning algorithm (...) are mined and analyzed for feature correlation. Based on the hidden association relationship of massive data, the study focuses on the implicit association mining of digital art features of data for the recommendation algorithm. The classification and continuous data feature attributes are introduced and discretized, and the binary representation of data features is extended to ensure the diversity of data feature attributes. In order to mine some correlation features in data, a heuristic feature mining method based on minimum support was studied to discover the frequency of correlation features and construct the optimal feature subset. Based on the frequent items of data features, this study observes the heuristic algorithm of digital art feature association mining based on minimum confidence and carries out feature matching based on digital art feature association mining under different situation modes. The validity of the proposed algorithm is verified by using the experimental data of health and medical situations in the machine learning library. (shrink)

Recent advances in machine learning methods have created opportunities to eliminate unfairness from algorithmic decision making. Multiple computational techniques (i.e., algorithmic fairness criteria) have arisen out of this work. Yet, urgent questions remain about the perceived fairness of these criteria and in which situations organizations should use them. In this paper, we seek to gain insight into these questions by exploring fairness perceptions of five algorithmic criteria. We focus on two key dimensions of fairness evaluations: distributive fairness and procedural (...) fairness. We shed light on variation in the potential for different algorithmic criteria to facilitate distributive fairness. Subsequently, we discuss procedural fairness and provide a framework for understanding how algorithmic criteria relate to essential aspects of this construct, which helps to identify when a specific criterion is suitable. From a practical standpoint, we encourage organizations to recognize that managing fairness in machine learning systems is complex, and that adopting a blind or one-size-fits-all mentality toward algorithmic criteria will surely damage people’s attitudes and trust in automated technology. Instead, firms should carefully consider the subtle yet significant differences between these technical solutions. (shrink)

Short-term traffic flow prediction is an effective means for intelligent transportation system to mitigate traffic congestion. However, traffic flow data with temporal features and periodic characteristics are vulnerable to weather effects, making short-term traffic flow prediction a challenging issue. However, the existing models do not consider the influence of weather changes on traffic flow, leading to poor performance under some extreme conditions. In view of the rich features of traffic data and the characteristic of being vulnerable to external weather (...) conditions, the prediction model based on traffic data has certain limitations, so it is necessary to conduct research studies on traffic flow prediction driven by both the traffic data and weather data. This paper proposes a combined framework of stacked autoencoder and radial basis function neural network to predict traffic flow, which can effectively capture the temporal correlation and periodicity of traffic flow data and disturbance of weather factors. Firstly, SAE is used to process the traffic flow data in multiple time slices to acquire a preliminary prediction. Then, RBF is used to capture the relation between weather disturbance and periodicity of traffic flow so as to gain another prediction. Finally, another RBF is used for the fusion of the above two predictions on decision level, obtaining a reconstructed prediction with higher accuracy. The effectiveness and robustness of the proposed model are verified by experiments. (shrink)

In order to better improve the teaching quality of university teachers, an effective method should be adopted for evaluation and analysis. This work studied the machine learning algorithms and selected the support vector machine (SVM) algorithm to evaluate teaching quality. First, the principles of selecting evaluation indexes were briefly introduced, and 16 evaluation indexes were selected from different aspects. Then, the SVM algorithm was used for evaluation. A genetic algorithm (GA)-SVM algorithm was designed and experimentally (...) analyzed. It was found that the training time and testing time of the GA-SVM algorithm were 23.21 and 7.25 ms, both of which were shorter than the SVM algorithm. In the evaluation of teaching quality, the evaluation value of the GA-SVM algorithm was closer to the actual value, indicating that the evaluation result was more accurate. The average accuracy of the GA-SVM algorithm was 11.64% higher than that of the SVM algorithm (98.36 vs 86.72%). The experimental results verify that the GA-SVM algorithm can have a good application in evaluating and analyzing teaching quality in universities with its advantages in efficiency and accuracy. (shrink)

Recent interest in the external validity of prediction models has produced many methods for finding predictive distributions that are invariant to dataset shifts and can be used for prediction in new, unseen environments. However, these methods consider different types of shifts and have been developed under disparate frameworks, making it difficult to theoretically analyze how solutions differ with respect to stability and accuracy. Taking a causal graphical view, we use a flexible graphical representation to express various types of dataset shifts. (...) Given a known graph of the data generating process, we show that all invariant distributions correspond to a causal hierarchy of graphical operators, which disable the edges in the graph that are responsible for the shifts. The hierarchy provides a common theoretical underpinning for understanding when and how stability to shifts can be achieved, and in what ways stable distributions can differ. We use it to establish conditions for minimax optimal performance across environments, and derive new algorithms that find optimal stable distributions. By using this new perspective, we empirically demonstrate that that there is a tradeoff between minimax and average performance. (shrink)

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

Software-controlled bots, also called social bots, are computer programs that act like human users on social media platforms. Recent work on detection of social bots is dominated by machine learning approaches. In this paper we explore bot detection as a model checking problem. We introduce Temporal Network Logic which we use to specify social networks where agents can post and follow each other. In this logic we formalize different types of social bot behavior. These are formulas that are (...) satisfied in a model of a network with bots. We provide a simple algorithm to extract a logical model from a real-life social network. We show that we can reduce TNL to a fragment of linear temporal logic with past and use this to establish the computational efficiency of model checking for social bot detection. (shrink)

Bilingualism has been identified as a potential cognitive factor linked to delayed onset of dementia as well as boosting executive functions in healthy individuals. However, more recently, this claim has been called into question following several failed replications. It remains unclear whether these contradictory findings reflect how bilingualism is defined between studies, or methodological limitations when measuring the bilingual effect. One key issue is that despite the claims that bilingualism yields general protection to cognitive processes, studies reporting putative bilingual differences (...) are often focused on domain specific experimental paradigms. This study chose a broader approach, by considering the consequences of bilingualism on a wide range of cognitive functions within individuals. We utilised 19 measures of different cognitive functions commonly associated with bilingual effects, to form a “cognitive profile” for 215 non-clinical participants. We recruited Welsh speakers, who as a group of bilinguals were highly homogeneous, as means of isolating the bilingualism criterion. We sought to determine if such analyses would independently classify bilingual/monolingual participant groups based on emergent patterns driven by collected cognitive profiles, such that population differences would emerge. Multiple predictive models were trained to independently recognise the cognitive profiles of bilinguals, older adults and higher education attainment. Despite managing to successfully classify cognitive profiles based on age and education, the model failed to differentiate between bilingual and monolingual cognitive ability at a rate greater than that of chance. Repeated modelling using alternative definitions of bilingualism, and just the older adults, yielded similar results. In all cases then, using our “bottom–up” analytical approach, there was no evidence that bilingualism as a variable indicated differential cognitive performance – as a consequence, we conclude that bilinguals are not cognitively different from their monolingual counterparts, even in older demographics. We suggest that studies that have reported a bilingual advantage could well have confounded other key variables that may be driving reported advantages. We recommend that future research refine the machine learning methods used in this study to further investigate the complex relationship between bilingualism and cognition. (shrink)

Bowers et al. argue that deep neural networks (DNNs) are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs are becoming larger-scale and increasingly more accurate, and prescribe methods for building DNNs that can reliably model biological vision.

This paper firstly designs a five-dimensional model of learners’ characteristics and a three-dimensional model of English reading resources’ characteristics in a fragmented learning environment through literature research. At the same time, to make the learning resources meet the characteristics of fragmented learning time and space, the English Level 4 reading resources are reasonably designed and segmented to adapt to the needs of learners’ mobile fragmented learning. Then, combined with machine learning algorithms, an adaptive recommendation model (...) of learning resources in English fragmented reading is constructed. The algorithm-based adaptive recommendation algorithm for English fragmented reading resources is designed. Based on the generated decision trees, the expression rules are parsed to achieve adaptive pushing of resources. The results of this study show that adaptive recommendation of learning resources in English fragmented reading can help teachers to develop future resource recommendation strategies through effective data collection to adaptively push resources that are close to learners’ individual needs. The use of mobile by English learners to learn to read in a fragmented learning context enables targeted training in weak areas of English reading, thus enhancing different aspects of learners’ reading skills. (shrink)

Most of the existing classification techniques concentrate on learning the datasets as a single similar unit, in spite of so many differentiating attributes and complexities involved. However, traditional classification techniques are required to analyze the datasets prior to learning, and if not doing so, they loss their performance in terms of accuracy and AUC. To this end, many of the machine learning problems can be very easily solved just by carefully observing human learning and training nature (...) and then mimicking the same in the machine learning. In response to these issues, we present a comprehensive suite of experiments carefully designed to provide conclusive, reliable, and significant results to the problem of efficient learning. This paper proposes a novel, simple, and effective machine learning paradigm that explicitly exploits this important similar-to-different (S2D) human learning strategy and implements it based on two algorithms (C4.5 and CART) efficiently. The framework not only analyzes the data sets prior to implementation, but also carefully allows classifier to have a systematic study so as to mimic the human training technique designed for efficient learning. Experimental results show that the method outperforms the state-of-the-art methods in terms of learning capability and breaks through the gap between human and machine learning. In fact, the proposed similar-to-different (S2D) strategy may also be useful in efficient learning of real-world complex and high-dimensional data sets, especially which are very typical to learn with traditional classifiers. (shrink)

It has been widely theorized and empirically proven that self-regulated learning is related to more desired learning outcomes, e.g., higher performance in transfer tests. Research has shifted to understanding the role of SRL during learning, such as the strategies and learning activities, learners employ and engage in the different SRL phases, which contribute to learning achievement. From a methodological perspective, measuring SRL using think-aloud data has been shown to be more insightful than self-report surveys as (...) it helps better in determining the link between SRL activities and learning achievements. Educational process mining on the basis of think-aloud data enables a deeper understanding and more fine-grained analyses of SRL processes. Although students’ SRL is highly contextualized, there are consistent findings of the link between SRL activities and learning outcomes pointing to some consistency of the processes that support learning. However, past studies have utilized differing approaches which make generalization of findings between studies investigating the unfolding of SRL processes during learning a challenge. In the present study with 29 university students, we measured SRL via concurrent think-aloud protocols in a pre-post design using a similar approach from a previous study in an online learning environment during a 45-min learning session, where students learned about three topics and wrote an essay. Results revealed significant learning gain and replication of links between SRL activities and transfer performance, similar to past research. Additionally, temporal structures of successful and less successful students indicated meaningful differences associated with both theoretical assumptions and past research findings. In conclusion, extending prior research by exploring SRL patterns in an online learning setting provides insights to the replicability of previous findings from online learning settings and new findings show that it is important not only to focus on the repertoire of SRL strategies but also on how and when they are used. (shrink)

Machine learning algorithms are increasingly used to shape high-stake allocations, sparking research efforts to orient algorithm design towards ideals of justice and fairness. In this research on algorithmic fairness, normative theorizing has primarily focused on identification of “ideally fair” target states. In this paper, we argue that this preoccupation with target states in abstraction from the situated dynamics of deployment is misguided. We propose a framework that takes dynamic trajectories as direct objects of moral appraisal, highlighting three respects (...) in which such trajectories can be subject to evaluation in relation to their temporal dynamics, robustness, and representation. (shrink)

Statistical learning enables humans to involuntarily process and utilize different kinds of patterns from the environment. However, the cognitive mechanisms underlying the simultaneous acquisition of multiple regularities from different perceptual modalities remain unclear. A novel multidimensional serial reaction time task was developed to test 40 participants’ ability to learn simple first‐order and complex second‐order relations between uni‐modal visual and cross‐modal audio‐visual stimuli. Using the difference in reaction times between sequenced and random stimuli as the index of domain‐general statistical (...) learning, a significant difference and dissociation of learning occurred between the initial and final learning phases. Furthermore, we used a negative and positive occurrence‐frequency‐and‐reaction‐time correlation to indicate implicit and explicit learning, respectively, and found that learning simple uni‐modal patterns involved an implicit‐to‐explicit segue, while acquiring complex cross‐modal patterns required an explicit‐to‐implicit segue, resulting in a X‐shape crossing of regularity learning. Thus, we propose an X‐way hypothesis to elucidate the dynamic interplay between the implicit and explicit systems at two distinct stages when acquiring various regularities in a multidimensional probability space. (shrink)

Objects in the world usually have names at different hierarchical levels (e.g., beagle, dog, animal). This research investigates adults' ability to use cross‐situational statistics to simultaneously learn object labels at individual and category levels. The results revealed that adults were able to use co‐occurrence information to learn hierarchical labels in contexts where the labels for individual objects and labels for categories were presented in completely separated blocks, in interleaved blocks, or mixed in the same trial. Temporal presentation schedules significantly (...) affected the learning of individual object labels, but not the learning of category labels. Learners' subsequent generalization of category labels indicated sensitivity to the structure of statistical input. (shrink)

To better reflect the precise clustering results of the data samples with different shapes and densities for affinity propagation clustering algorithm, an improved integrated clustering learning strategy based on three-stage affinity propagation algorithm with density peak optimization theory was proposed in this paper. DPKT-AP combined the ideology of integrated clustering with the AP algorithm, by introducing the density peak theory and k-means algorithm to carry on the three-stage clustering process. In the first stage, the clustering (...) center point was selected by density peak clustering. Because the clustering center was surrounded by the nearest neighbor point with lower local density and had a relatively large distance from other points with higher density, it could help the k-means algorithm in the second stage avoiding the local optimal situation. In the second stage, the k-means algorithm was used to cluster the data samples to form several relatively small spherical subgroups, and each of subgroups had a local density maximum point, which is called the center point of the subgroup. In the third stage, DPKT-AP used the AP algorithm to merge and cluster the spherical subgroups. Experiments on UCI data sets and synthetic data sets showed that DPKT-AP improved the clustering performance and accuracy for the algorithm. (shrink)

The dependency of a speech recognition system on the accent of a user leads to the variation in its performance, as the people from different backgrounds have different accents. Accent labeling and conversion have been reported as a prospective solution for the challenges faced in language learning and various other voice-based advents. In the English TTS system, the accent labeling of unregistered words is another very important link besides the phonetic conversion. Since the importance of the primary stress is (...) much greater than that of the secondary stress, and the primary stress is easier to call than the secondary stress, the labeling of the primary stress is separated from the secondary stress. In this work, the labeling of primary accents uses a labeling algorithm that combines morphological rules and machine learning; the labeling of secondary accents is done entirely through machine learning algorithms. After 10 rounds of cross-validation, the average tagging accuracy rate of primary stress was 94%, the average tagging accuracy rate of secondary stress was 94%, and the total tagging accuracy rate was 83.6%. This perceptual study separates the labeling of primary and secondary accents providing the promising outcomes. (shrink)

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

In this paper, we simulate the estimation of motion through an interframe difference detection function model and investigate the spatial-temporal context information correlation filtering target tracking algorithm, which is complex and computationally intensive. The basic theory of spatiotemporal context information and correlation filtering is studied to construct a fast target tracking method. The different computational schemes are designed for the flow of multiframe target detection from background removal to noise reduction, to single-frame detection, and finally to multiframe (...) detection, respectively. This enables the ground-based telescope to effectively detect spatial targets in dense stellar backgrounds in both modes. The method is validated by simulations and experiments and can meet the requirements of real projects. The interframe bit attitude estimation is optimized by using the beam-parity method to reduce the interframe estimation noise; a global optimization strategy based on the bit attitude map is used in the back end to reduce the system computation amount and make the global bit attitude estimation more accurate; a loop detection based on the word pocket model is added to the system to reduce the cumulative error. (shrink)

It is well known that the unpredictable speech production brought on by stress from the task at hand has a significant negative impact on the performance of speech processing algorithms. Speech therapy benefits from being able to detect stress in speech. Speech processing performance suffers noticeably when perceptually produced stress causes variations in speech production. Using the acoustic speech signal to objectively characterize speaker stress is one method for assessing production variances brought on by stress. Real-world complexity and ambiguity make (...) it difficult for decision-makers to express their conclusions with clarity in their speech. In particular, the Neutrosophic speech algorithm is used to encode the language variables because they cannot be computed directly. Neutrosophic sets are used to manage indeterminacy in a practical situation. Existing algorithms are used except for stress on Neutrosophic speech recognition. The creation of algorithms that calculate, categorize, or differentiate between different stress circumstances. Understanding stress and developing strategies to combat its effects on speech recognition and human-computer interaction system are the goals of this recognition. (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)

Forecasting blood glucose values for patients can help prevent hypoglycemia and hyperglycemia events in advance. To this end, this study proposes an intelligent ensemble deep learning system to predict BG values in 15, 30, and 60 min prediction horizons based on historical BG values collected via continuous glucose monitoring devices as an endogenous factor and carbohydrate intake and insulin administration information as exogenous factors. Although there are numerous deep learning algorithms available, this study applied five algorithms, namely, recurrent (...) neural network, which is optimized for sequence data, and RNN-based algorithms, stacked LSTM, bidirectional LSTM, and gated recurrent unit). Then, a genetic algorithm was applied to the five prediction models to optimize their weights through ensemble techniques and to yield the final predicted BG values. The performance of the proposed model was compared to that of the autoregressive integrated moving average model as a baseline. The results show that the proposed model significantly outperforms the baseline in terms of the root mean square error and continuous glucose error grid analysis. For the valid 29 diabetic patients for the multivariate models, the RMSE was 11.08, 19.25, and 31.30 mg/DL for 15, 30, and 60 min PH, respectively. When the same data were applied to univariate models, the RMSE was 11.28, 19.99, and 33.13 mg/DL for 15, 30, and 60 min PH, respectively. Both the univariate and multivariate models showed a statistically significant difference compared with the baseline at a 5% statistical significance level. Instead of using a model with a single algorithm, applying a GA based on each output of a model with multiple algorithms was found to play a significant role in improving model performance. (shrink)

Industry 4.0 The present work enables us to take the first steps in the world of the 4th Industrial Revolution, a world where robots, artificial intelligence and digital manufacturing technologies will change forever the way we design, produce and buy products and services. The first characteristics of this revolution is globalization: for the first time in history, an industrial transformation is taking place simultaneously on a global scale. The second key-factor is the word ecosystem: unlike the first three industrial revolutions (...) (steam engine, electricity and computers) over the past few years, no technologies nor machines were invented anew, but we understood how to keep together different technological platforms by using the same language (bit). If the revolution in place will complete the transformations announced, in twenty years we will look at today’s society the same way we nowadays look at the 19th Century society. (shrink)

In view of the poor recommendation performance of traditional resource collaborative filtering recommendation algorithms, this article proposes a collaborative filtering recommendation model based on deep learning for art and MOOC resources. This model first uses embedding vectors based on the context of metapaths for learning. Embedding vectors based on the context of metapaths aggregate different metapath information and different MOOCs may have different preferences for different metapaths. Secondly, to capture this preference drift, the model introduces an attention mechanism, (...) which can improve the interpretability of the recommendation results. Then, by introducing the Laplacian matrix into the prior distribution of the hidden factor feature matrix, the relational network information is effectively integrated into the model. Finally, compared with the traditional model using the scoring matrix, the model in this article using text word vectors effectively alleviates the impact of data sparsity and greatly improves the accuracy of prediction. After analyzing the experimental results, compared with other algorithms, the resource collaborative filtering recommendation model proposed in this article has achieved better recommendation results, with good stability and scalability. (shrink)

Deep learning algorithms are rapidly changing the way in which audiovisual media can be produced. Synthetic audiovisual media generated with deep learning—often subsumed colloquially under the label “deepfakes”—have a number of impressive characteristics; they are increasingly trivial to produce, and can be indistinguishable from real sounds and images recorded with a sensor. Much attention has been dedicated to ethical concerns raised by this technological development. Here, I focus instead on a set of issues related to the notion of (...) synthetic audiovisual media, its place within a broader taxonomy of audiovisual media, and how deep learning techniques differ from more traditional approaches to media synthesis. After reviewing important etiological features of deep learning pipelines for media manipulation and generation, I argue that “deepfakes” and related synthetic media produced with such pipelines do not merely offer incremental improvements over previous methods, but challenge traditional taxonomical distinctions, and pave the way for genuinely novel kinds of audiovisual media. (shrink)

It has consistently been shown that agents judge the intervals between their actions and outcomes as compressed in time, an effect named intentional binding. In the present work, we investigated whether this effect is result of prior bias volunteers have about the timing of the consequences of their actions, or if it is due to learning that occurs during the experimental session. Volunteers made temporal estimates of the interval between their action and target onset , or between two (...) events . Our results show that temporal estimates become shorter throughout each experimental block in both conditions. Moreover, we found that observers judged intervals between action and outcomes as shorter even in very early trials of each block. To quantify the decrease of temporal judgments in experimental blocks, exponential functions were fitted to participants’ temporal judgments. The fitted parameters suggest that observers had different prior biases as to intervals between events in which action was involved. These findings suggest that prior bias might play a more important role in this effect than calibration-type learning processes. (shrink)

As one of the traditional entertainment items, video background music has gradually changed from traditional consumption to network consumption, which naturally also has the problem of information overload. From the perspective of model design and auxiliary information, this paper proposes a tightly coupled fusion model based on deep learning and collaborative filtering to alleviate the problem of poor prediction accuracy due to sparse matrix in the scoring prediction problem. In the use of auxiliary information, this paper uses crawler technology (...) to obtain auxiliary information on the user side and the video background music side and compensates for the model’s sensitivity to the sparsity of the score matrix from a data perspective. In terms of model design, this paper conducts auxiliary information mining based on the diversity and structural differences of auxiliary information, uses an improved stack autoencoder to learn user’s interests, and uses convolutional neural networks to mine hidden features of video background music. Based on the idea of probabilistic matrix decomposition, the tightly coupled fusion of multiple deep learning models and collaborative filtering is realized. By comprehensively considering user’s interest and video background music characteristics, the collaborative filtering process is supervised, and the optimized prediction result is finally obtained. The performance test and function test of the system were carried out, respectively, to verify the effectiveness of the hybrid recommendation algorithm and the effect of the system for recommendation. Through experimental analysis, it is proved that the algorithm designed in this paper can improve the recommendation quality and achieve the expected goal. (shrink)

Human gait is a complex activity that requires high coordination between the central nervous system, the limb, and the musculoskeletal system. More research is needed to understand the latter coordination's complexity in designing better and more effective rehabilitation strategies for gait disorders. Electroencephalogram and functional near-infrared spectroscopy are among the most used technologies for monitoring brain activities due to portability, non-invasiveness, and relatively low cost compared to others. Fusing EEG and fNIRS is a well-known and established methodology proven to enhance (...) brain–computer interface performance in terms of classification accuracy, number of control commands, and response time. Although there has been significant research exploring hybrid BCI involving both EEG and fNIRS for different types of tasks and human activities, human gait remains still underinvestigated. In this article, we aim to shed light on the recent development in the analysis of human gait using a hybrid EEG-fNIRS-based BCI system. The current review has followed guidelines of preferred reporting items for systematic reviews and meta-Analyses during the data collection and selection phase. In this review, we put a particular focus on the commonly used signal processing and machine learning algorithms, as well as survey the potential applications of gait analysis. We distill some of the critical findings of this survey as follows. First, hardware specifications and experimental paradigms should be carefully considered because of their direct impact on the quality of gait assessment. Second, since both modalities, EEG and fNIRS, are sensitive to motion artifacts, instrumental, and physiological noises, there is a quest for more robust and sophisticated signal processing algorithms. Third, hybrid temporal and spatial features, obtained by virtue of fusing EEG and fNIRS and associated with cortical activation, can help better identify the correlation between brain activation and gait. In conclusion, hBCI system is not yet much explored for the lower limb due to its complexity compared to the higher limb. Existing BCI systems for gait monitoring tend to only focus on one modality. We foresee a vast potential in adopting hBCI in gait analysis. Imminent technical breakthroughs are expected using hybrid EEG-fNIRS-based BCI for gait to control assistive devices and Monitor neuro-plasticity in neuro-rehabilitation. However, although those hybrid systems perform well in a controlled experimental environment when it comes to adopting them as a certified medical device in real-life clinical applications, there is still a long way to go. (shrink)

The application of machine-learning technologies to medical practice promises to enhance the capabilities of healthcare professionals in the assessment, diagnosis, and treatment, of medical conditions. However, there is growing concern that algorithmic bias may perpetuate or exacerbate existing health inequalities. Hence, it matters that we make precise the different respects in which algorithmic bias can arise in medicine, and also make clear the normative relevance of these different kinds of algorithmic bias for broader questions about justice and fairness in (...) healthcare. In this paper, we provide the building blocks for an account of algorithmic bias and its normative relevance in medicine. (shrink)

This article examines the complaint that arbitrary algorithmic decisions wrong those whom they affect. It makes three contributions. First, it provides an analysis of what arbitrariness means in this context. Second, it argues that arbitrariness is not of moral concern except when special circumstances apply. However, when the same algorithm or different algorithms based on the same data are used in multiple contexts, a person may be arbitrarily excluded from a broad range of opportunities. The third contribution is to (...) explain why this systemic exclusion is of moral concern and to offer a solution to address it. (shrink)

Recent influential accounts of temporal representation—the use of mental representations with explicit temporal contents, such as before and after relations and durations—sharply distinguish representation from mere sensitivity. A common, important picture of inter-temporal rationality is that it consists in maximizing total expected discounted utility across time. By analyzing reinforcement learning algorithms, this article shows that, given such notions of temporal representation and inter-temporal rationality, it would be possible for an agent to achieve inter-temporal (...) rationality without temporal representation. It then explores potential upshots of this result for theorizing about rationality and representation. (shrink)

Convolutional neural networks, which automatically learn features from raw data to approximate functions, are being increasingly applied to the end-to-end analysis of electroencephalographic signals, especially for decoding brain states in brain-computer interfaces. Nevertheless, CNNs introduce a large number of trainable parameters, may require long training times, and lack in interpretability of learned features. The aim of this study is to propose a CNN design for P300 decoding with emphasis on its lightweight design while guaranteeing high performance, on the effects of (...) different training strategies, and on the use of post-hoc techniques to explain network decisions. The proposed design, named MS-EEGNet, learned temporal features in two different timescales in an efficient and optimized way, and was validated on three P300 datasets. The CNN was trained using different strategies and was compared with several state-of-the-art algorithms. Furthermore, variants of the baseline MS-EEGNet were analyzed to evaluate the impact of different hyper-parameters on performance. Lastly, saliency maps were used to derive representations of the relevant spatio-temporal features that drove CNN decisions. MS-EEGNet was the lightest CNN compared with the tested SOA CNNs, despite its multiple timescales, and significantly outperformed the SOA algorithms. Post-hoc hyper-parameter analysis confirmed the benefits of the innovative aspects of MS-EEGNet. Furthermore, MS-EEGNet did benefit from transfer learning, especially using a low number of training examples, suggesting that the proposed approach could be used in BCIs to accurately decode the P300 event while reducing calibration times. Representations derived from the saliency maps matched the P300 spatio-temporal distribution, further validating the proposed decoding approach. This study, by specifically addressing the aspects of lightweight design, transfer learning, and interpretability, can contribute to advance the development of deep learning algorithms for P300-based BCIs. (shrink)

This contribution aims at proposing a framework for articulating different kinds of “normativities” that are and can be attributed to “algorithmic systems.” The technical normativity manifests itself through the lineage of technical objects. The norm expresses a technical scheme’s becoming as it mutates through, but also resists, inventions. The genealogy of neural networks shall provide a powerful illustration of this dynamic by engaging with their concrete functioning as well as their unsuspected potentialities. The socio-technical normativity accounts for the manners in (...) which engineers, as actors folded into socio-technical networks, willingly or unwittingly, infuse technical objects with values materialized in the system. Surveillance systems’ design will serve here to instantiate the ongoing mediation through which algorithmic systems are endowed with specific capacities. The behavioral normativity is the normative activity, in which both organic and mechanical behaviors are actively participating, undoing the identification of machines with “norm following,” and organisms with “norminstitution”. This proposition productively accounts for the singularity of machine learning algorithms, explored here through the case of recommender systems. The paper will provide substantial discussions of the notions of “normative” by cutting across history and philosophy of science, legal, and critical theory, as well as “algorithmics,” and by confronting our studies led in engineering laboratories with critical algorithm studies. (shrink)

Algorithm Decision Making (ADM) systems designed to augment or automate human decision-making have the potential to produce better decisions while also freeing up human time and attention for other pursuits. For this potential to be realised, however, algorithmic decisions must be sufficiently aligned with human goals and interests. We take a Principal-Agent (P-A) approach to the questions of ADM alignment and trust. In a broad sense, ADM is beneficial if and only if human principals can trust algorithmic agents to (...) act faithfully on their behalf. This mirrors the challenge of facilitating P-A relationships among humans, but the peculiar nature of human-machine interaction also raises unique issues. The problem of asymmetric information is omnipresent but takes a different form in the context of ADM. Although the decision-making machinery of an algorithmic agent can in principle be laid bare for all to see, the sheer complexity of ADM systems based on deep learning models prevents straightforward monitoring. We draw on literature from economics and political science to argue that the problem of trust in ADM systems should be addressed at the level of institutions. Although the dyadic relationship between human principals and algorithmic agents is our ultimate concern, cooperation at this level must rest against an institutional environment which allows humans to effectively evaluate and choose among algorithmic alternatives. (shrink)

Evidence from neurophysiological and psychological studies is coming together to shed light on how we represent and recognize objects. This review describes evidence supporting two major hypotheses: the first is that objects are represented in a mosaic-like form in which objects are encoded by combinations of complex, reusable features, rather than two-dimensional templates, or three-dimensional models. The second hypothesis is that transform-invariant representations of objects are learnt through experience, and that this learning is affected by the temporal sequence (...) in which different views of the objects are seen, as well as by their physical appearance. (shrink)

Liquidity risk arises from the inability to unwind or hedge trading positions at the prevailing market prices. The risk of liquidity is a wide and complex topic as it depends on several factors and causes. While much has been written on the subject, there exists no clear-cut mathematical description of the phenomena and typical market risk modeling methods fail to identify the effect of illiquidity risk. In this paper, we do not propose a definitive one either, but we attempt to (...) derive novel mathematical algorithms for the dynamic modeling of trading volumes during the closeout period from the perspective of multiple-asset portfolio, as well as for financial entities with different subsidiary firms and multiple agents. The robust modeling techniques are based on the application of initial-value-problem differential equations technique for portfolio selection and risk management purposes. This paper provides some crucial parameters for the assessment of the trading volumes of multiple-asset portfolio during the closeout period, where the mathematical proofs for each theorem and corollary are provided. Based on the new developed econophysics theory, this paper presents for the first time a closed-form solution for key parameters for the estimation of trading volumes and liquidity risk, such as the unwinding constant, half-life, and mean lifetime and discusses how these novel parameters can be estimated and incorporated into the proposed techniques. The developed modeling algorithms are appealing in terms of theory and are promising for practical econophysics applications, particularly in developing dynamic and robust portfolio management algorithms in light of the 2007–2009 global financial crunch. In addition, they can be applied to artificial intelligence and machine learning for the policymaking process, reinforcement machine learning techniques for the Internet of Things data analytics, expert systems in finance, FinTech, and within big data ecosystems. (shrink)

Recommending the identity of bidders in public procurement auctions has a significant impact in many areas of public procurement, but it has not yet been studied in depth. A bidders recommender would be a very beneficial tool because a supplier can search appropriate tenders and, vice versa, a public procurement agency can discover automatically unknown companies which are suitable for its tender. This paper develops a pioneering algorithm to recommend potential bidders using a machine learning method, particularly a (...) random forest classifier. The bidders recommender is described theoretically, so it can be implemented or adapted to any particular situation. It has been successfully validated with a case study: an actual Spanish tender dataset which has 102,087 tenders from 2014 to 2020 and a company dataset which has 1,353,213 Spanish companies. Quantitative, graphical, and statistical descriptions of both datasets are presented. The results of the case study were satisfactory: the winning bidding company is within the recommended companies group, from 24% to 38% of the tenders, according to different test conditions and scenarios. (shrink)

In a time of big data, thinking about how we are seen and how that affects our lives means changing our idea about who does the seeing. Data produced by machines is most often ‘seen’ by other machines; the eye is in question is algorithmic. Algorithmic seeing does not produce a computational panopticon but a mechanism of prediction. The authority of its predictions rests on a slippage of the scientific method in to the world of data. Data science inherits some (...) of the problems of science, especially the disembodied ‘view from above’, and adds new ones of its own. As its core methods like machine learning are based on seeing correlations not understanding causation, it reproduces the prejudices of its input. Rising in to the apparatuses of governance, it reinforces the problematic sides of ‘seeing like a state’ and links to the recursive production of paranoia. It forces us to ask the question ‘what counts as rational seeing?’. Answering this from a position of feminist empiricism reveals different possibilities latent in seeing with machines. Grounded in the idea of conviviality, machine learning may reveal forgotten non-market patterns and enable free and critical learning. It is proposed that a programme to challenge the production of irrational pre-emption is also a search for the possibility of algorithmic conviviality. (shrink)