We discuss the role of perceptron (or threshold) connectives in the context of Description Logic, and in particular their possible use as a bridge between statistical learning of models from data and logical reasoning over knowledge bases. We prove that such connectives can be added to the language of most forms of Description Logic without increasing the complexity of the corresponding inference problem. We show, with a practical example over the Gene Ontology, how even simple instances of perceptron (...) connectives are expressive enough to represent learned, complex concepts derived from real use cases. This opens up the possibility to import concepts learnt from data into existing ontologies. (shrink)

We study the finitely repeated prisoner’s dilemma in which the players are restricted to choosing strategies which are implementable by a machine with a bound on its complexity. One player has to use a finite automaton while the other player has to use a finite perceptron. Some examples illustrate that the sets of strategies which are induced by these two types of machines are different and not ordered by set inclusion. Repeated game payoffs are evaluated according to the limit (...) of means. The main result establishes that a cooperation at almost all stages of the game is an equilibrium outcome if the complexity of the machines the players may use is limited enough and if the length T of the repeated game is sufficiently large. This result persists when more than T states are allowed in the player’s automaton. We further consider a variant of the model in which the two players are restricted to choosing strategies which are implementable by perceptrons and prove that the players can cooperate at most of the stages provided that the complexity of their perceptrons is sufficiently reduced. (shrink)

If we are eventually to understand the capability of higher organisms for perceptual recognition, generalization, recall, and thinking, we must first have answers to three fundamental questions: 1. How is information about the physical world sensed, or detected, by the biological system? 2. In what form is information stored, or remembered? 3. How does information contained in storage, or in memory, influence recognition and behavior? The first of these questions is in the.

Van Gelder's example of a dynamical model is a Perceptron. The similarity of dynamical models and Perceptrons in turn exemplifies the close relationship between dynamical and algorithmic models. Both are models, not literal descriptions of brains. The brain states of standard modeling are better conceived as processes in the dynamical sense, but algorithmic models remain useful.

A roomsize computer equipped with a new type of circuitry, the Perceptron, was introduced to the world in 1958 in a brief news story buried deep in The New York Times. The story cited the U.S. Navy as saying that the Perceptron would lead to machines that “will be able to walk, talk, see, write, reproduce itself and be conscious of its existence.” More than six decades later, similar claims are being made about current artificial intelligence. So, what’s (...) changed in the intervening years? In some ways, not much. (shrink)

We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim is, firstly, to (...) target a model-agnostic distillation approach exemplified with these two frameworks, secondly, to study how these two frameworks interact on a theoretical level, and, thirdly, to investigate use-cases in ML and AI in a comparative manner. Specifically, we envision that user-studies will help determine human understandability of explanations generated using these two frameworks. (shrink)

1 Cognitive Architectures 2 Multilayer Perceptrons 3 Relations between Variables 4 Structured Representations 5 Individuals 6 Where does the Machinery of Symbol Manipulation Come From? 7 Conclusions.

In this paper an Artificial Neural Network (ANN) model, for predicting the category of a tumor was developed and tested. Taking patients’ tests, a number of information gained that influence the classification of the tumor. Such information as age, sex, histologic-type, degree-of-diffe, status of bone, bone-marrow, lung, pleura, peritoneum, liver, brain, skin, neck, supraclavicular, axillar, mediastinum, and abdominal. They were used as input variables for the ANN model. A model based on the Multilayer Perceptron Topology was established and trained (...) using data set which its title is “primary tumor” and was obtained from the University Medical Centre, Institute of Oncology, Ljubljana, Yugoslavia Test data evaluation shows that the ANN model is able to correctly predict the tumor category with 76.67 % accuracy. (shrink)

We question the widespread assumption that linguistic theory should guide the formulation of mechanistic accounts of human language processing. We develop a pseudo‐linguistic theory for the domain of linguistic stress, based on observation of the learning behavior of a perceptron exposed to a variety of stress patterns. There are significant similarities between our analysis of perception stress learning and metrical phonology, the linguistic theory of human stress. Both approaches attempt to identify salient characteristics of the stress systems under examination (...) without reference to the workings of the underlying processor. Our theory and computer simulations exhibit some strikingly suggestive correspondences with metrical theory. We show, however, that our high‐level pseudo‐linguistic account bears no causal relation to processing in the perception, and provides little insight into the nature of this processing. Because of the persuasive similarities between the nature of our theory and linguistic theorizing, we suggest that linguistic theory may be in much the same position. Contrary to the usual assumption, it may not provide useful guidance in attempts to identify processing mechanisms underlying human language. (shrink)

Compared to constraint-based causal discovery, causal discovery based on functional causal models is able to identify the whole causal model under appropriate assumptions [Shimizu et al. 2006; Hoyer et al. 2009; Zhang and Hyvärinen 2009b]. Functional causal models represent the effect as a function of the direct causes together with an independent noise term. Examples include the linear non-Gaussian acyclic model, nonlinear additive noise model, and post-nonlinear model. Currently, there are two ways to estimate the parameters in the models: dependence (...) minimization and maximum likelihood. In this article, we show that for any acyclic functional causal model, minimizing the mutual information between the hypothetical cause and the noise term is equivalent to maximizing the data likelihood with a flexible model for the distribution of the noise term. We then focus on estimation of the PNL causal model and propose to estimate it with the warped Gaussian process with the noise modeled by the mixture of Gaussians. As a Bayesian nonparametric approach, it outperforms the previous one based on mutual information minimization with nonlinear functions represented by multilayer perceptrons; we also show that unlike the ordinary regression, estimation results of the PNL causal model are sensitive to the assumption on the noise distribution. Experimental results on both synthetic and real data support our theoretical claims. (shrink)

Current artificial neural network or connectionist models of music cognition embody feature-extraction and feature-weighting principles. This paper reports two experiments which seek evidence for similar processes mediating recognition of short musical compositions by musically trained and untrained listeners. The experiments are cast within a pattern recognition framework based on the vision-audition analogue wherein music is considered an auditory pattern consisting of local and global features. Local features such as inter-note interval, and global features such as melodic contour, are derived from (...) a two-dimensional matrix in which music is represented as a series of frequencies plotted over time.Manipulation of inter-note interval affected accuracy and reaction time measures in a discrimination task, whereas the same variables were affected by manipulation of melodic contour in a classification task. Musical training is thought of as a form of practice in musical pattern recognition and, as predicted, accuracy and reaction time measures of musically trained subjects were significantly better than those of untrained subjects. Given the evidence for feature-extraction and weighting processes in music recognition tasks, two connectionist models are discussed. The first is a single-layer perceptron which has been trained to discriminate between compositions according to inter-note interval. A second network, using the back-propagation algorithm and sequential input of patterns, is also discussed. (shrink)

The purpose of this paper is to identify the factors that affect the intention to use Big Data Applications in companies. Research into Big Data usage intention and adoption is scarce and much less from the perspective of the use of these techniques in companies. That is why this research focuses on analyzing the adoption of Big Data Applications by companies. Further to a review of the literature, it is proposed to use a UTAUT model as a starting model with (...) the update and incorporation of other variables such as resistance to use and perceived risk, and then to perform a neural network to predict this adoption. With respect to this non-parametric technique, we found that the multilayer perceptron model (MLP) for the use of Big Data Applications in companies obtains higher AUC values, and a better confusion matrix. This paper is a pioneering study using this hybrid methodology on the intention to use Big Data Applications. The result of this research has important implications for the theory and practice of adopting Big Data Applications. (shrink)

In relation to semantics, “grounding” has two relevant meanings. “Symbol grounding” is the process of connecting symbols to perception and the world. “Communicative grounding” is the process of interactively adding to common ground in dialog. Strategies for grounding in human communication include, crucially, strategies for resolving troubles caused by various kinds of miscommunication. As it happens, these two processes of grounding are closely related. As a side-effect of grounding an utterance, dialog participants may adjust the meanings they assign to linguistic (...) expressions, in a process of semantic coordination. Meanings of at least some expressions include perceptual aspects which enable DPs to classify entities as falling under the expression or not based on their perception of those entities. We show how perceptual grounding of symbols can be achieved in a process of interactively adding to common ground. This requires that perceptual aspects of meaning can be updated as a result of participating in linguistic interaction, thereby enabling fine-grained semantic coordination of perceptually grounded linguistic meanings. A formal semantics for low-level perceptual aspects of meaning is presented, tying these together with the logical-inferential aspects of meaning traditionally studied in formal semantics. The key idea is to model perceptual meanings as classifiers of perceptual input. This requires a framework where intensions are represented independently of extensions, and structured objects which can be modified as a result of learning. We use Type Theory with Records, a formal semantics framework which starts from the idea that information and meaning are founded on our ability to perceive and classify the world, that is, to perceive objects and situations as being of types. As an example of our approach, we show how a simple classifier of spatial information based on the Perceptron can be cast in TTR. (shrink)

This paper aims to introduce a robust framework for forecasting demand, including data preprocessing, data transformation and standardization, feature selection, cross-validation, and regression ensemble framework. Bagging ), boosting and extreme gradient boosting regression ), and stacking are employed as ensemble models. Different machine learning approaches, including support vector regression, extreme learning machine, and multilayer perceptron neural network, are adopted as reference models. In order to maximize the determination coefficient value and reduce the root mean square error, hyperparameters are set (...) using the grid search method. Using a steel industry dataset, all tests are carried out under identical experimental conditions. In this context, STACK1 and STACK2 models provided better performance than other models. The highest accuracies of R2 of 0.97 and 0.97 are obtained using STACK1 and STACK2, respectively. Moreover, the rank according to performances is STACK1, STACK2, XGBR, GBR, RFR, MLP, ELM, and SVR. As it improves the performance of models and reduces the risk of decision-making, the ensemble method can be used to forecast the demand in a steel industry one month ahead. (shrink)

Evapotranspiration represents the water requirement of plants during their growing season, and its accurate measurement at the farm is essential for agricultural water planners and managers. Field measurements of evapotranspiration have always been associated with many difficulties that have led researchers to seek a way to remotely measure this component in horticultural and agricultural areas. This study aims to investigate an indirect approach for daily rice crop evapotranspiration measurement by machine learning techniques and the least available climatic variables. For this (...) purpose, daily meteorological variables were obtained from three ground meteorological stations in rice cultivation regions of northern Iran during 2003–2016. The ETc rates were calculated by seven meteorological variables, the FAO-56 Penman-Monteith equation, and the regional calibrated rice crop coefficient and considered as the reference data. The MLs, including Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Network, and Group Method of Data Handling, were utilized for ETc modeling. Different input combinations were applied, based on the use of minimum effective variables as input. Results showed that the models showed the most accurate performances in the input combination of four climatic variables: sunshine duration, maximum temperature, relative humidity, and wind speed. Investigating the accuracy of models in rice growth phases showed that the least estimation error belonged to the initial growing stage, which increased during the mid-season and late-season growing stages. A comparison of the models showed that the GMDH model performed better against the other competitors. For this model, both the Nash-Sutcliffe coefficient and R2 were greater than 0.98, and the Root Mean Square Error ranged between 0.214 and 0.234 mm per day in all stations. The current approach showed promising results in rice evapotranspiration modeling by only four common meteorological variables and can be reliably applied for indirect measurement of this variable over the rice farms. The studied approach will have research value for rice and other crops in similar/different climatic conditions. (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)

The car-sharing system is a popular rental model for cars in shared use. It has become particularly attractive due to its flexibility; that is, the car can be rented and returned anywhere within one of the authorized parking slots. The main objective of this research work is to predict the car usage in parking stations and to investigate the factors that help to improve the prediction. Thus, new strategies can be designed to make more cars on the road and fewer (...) in the parking stations. To achieve that, various machine learning models, namely vector autoregression, support vector regression, eXtreme gradient boosting, k-nearest neighbors, and deep learning models specifically long short-time memory, gated recurrent unit, convolutional neural network, CNN-LSTM, and multilayer perceptron, were performed on different kinds of features. These features include the past usage levels, Chongqing’s environmental conditions, and temporal information. After comparing the obtained results using different metrics, we found that CNN-LSTM outperformed other methods to predict the future car usage. Meanwhile, the model using all the different feature categories results in the most precise prediction than any of the models using one feature category at a time. (shrink)

The foremost aim of this research was to forecast the performance of three stock market indices using the multilayer perceptron, recurrent neural network, and autoregressive integrated moving average on historical data. Moreover, we compared the extrapolative abilities of a hybrid of ARIMA with MLP and RNN models, which are called ARIMA-MLP and ARIMA-RNN. Because of the complicated and noisy nature of financial data, we combine novel machine-learning techniques such as MLP and RNN with ARIMA model to predict the three (...) stock market data. The data used in this study are taken from the Pakistan Stock Exchange, National Stock Exchange India, and Sri Lanka Stock Exchange. In the case of Pakistan, the findings show that the ARIMA-MLP and ARIMA-RNN beat the individual ARIMA, MLP, and RNN models in terms of accuracy. Similarly, in the case of Sri Lanka and India, the hybrid models show more robustness in terms of forecasting than individual ARIMA, MLP, and RNN models based on root-mean-square error and mean absolute error. Apart from this, ARIMA-MLP outperformed the ARIMA-RNN in the case of Pakistan and India, while in the context of Sri Lanka, ARIMA-RNN beat the ARIMA-MLP in forecasting. Our findings reveal that the hybrid models can be regarded as a suitable option for financial time-series forecasting. (shrink)

Rogers & McClelland (R&M) have provided an impressive outline of the capabilities of a class of multi-layered perceptrons that mimic many aspects of human knowledge acquisition. Despite this success, in the literature several basic issues are raised and concerns are expressed. Indeed, the problems are so acute that a different way of thinking is called for. In this commentary it is suggested that rational models approach provides a promising alternative.

As the stock market is an important part of the national economy, more and more investors have begun to pay attention to the methods to improve the return on investment and effectively avoid certain risks. Many factors affect the trend of the stock market, and the relevant information has the nature of time series. This paper proposes a composite model CNN-BiSLSTM to predict the closing price of the stock. Bidirectional special long short-term memory improved on bidirectional long short-term memory adds (...) 1 − tanh function in the output gate which makes the model better predict the stock price. The model extracts advanced features that influence stock price through convolutional neural network, and predicts the stock closing price through BiSLSTM after the data processed by CNN. To verify the effectiveness of the model, the historical data of the Shenzhen Component Index from July 1, 1991, to October 30, 2020, are used to train and test the CNN-BiSLSTM. CNN-BiSLSTM is compared with multilayer perceptron, recurrent neural network, long short-term memory, BiLSTM, CNN-LSTM, and CNN-BiLSTM. The experimental results show that the mean absolute error, root-mean-squared error, and R-square evaluation indicators of the CNN-BiSLSTM are all optimal. Therefore, CNN-BiSLSTM can accurately predict the closing price of the Shenzhen Component Index of the next trading day, which can be used as a reference for the majority of investors to effectively avoid certain risks. (shrink)

Objective. Study of the validity and reliability of the discourse approach for the psycholinguistic understanding of the nature, structure, and features of the linguistic consciousness functioning. -/- Materials & Methods. This paper analyzes artificial neural network models built on the corpus of texts, which were obtained in the process of experimental research of the coronavirus quarantine concept as a new category of linguistic consciousness. The methodology of feedforward artificial neural networks (multilayer perceptron) was used in order to assess the (...) possibility of predicting the leading texts semantics based on the discourses ranks and their place in the respective linear sequence. Same baseline parameters were used to predict respondents' self-assessments of changes in their psychological well-being and in daily life routine during the quarantine, as well as to predict their preferences of the quarantine strategies. The study relied on basic ideas about discourse as a meaning constituted by the dispersion of other meanings (Foucault). The same dispersion mechanism realizes itself in interdiscourse interaction, forming a discursive formation at a higher level. The method of T-units (Hunt) was used to identify and count discourses in the texts. The ranking of discourses was provided based on the criterion of their semantic-syntactic autonomy. -/- Results. The conducted neural network modeling revealed a high accuracy in predicting the work of the linguistic consciousness functions associated with retrospective self-assessment and anticipatory imagination of the respondents. Another result of this modeling is a partial confirmation of the assumption concerning existence a relationship between the structural parameters of the discursive field (the rank of the discourses and their place in the respective linear sequence) and the leading semantics of the text. -/- Conclusions. A discourse approach to the study of linguistic consciousness, understanding of its structure and functioning features seems to be reasonably appropriate. The implementation of the approach presupposes the need to form a base of linguistic corpora with the inclusion in each text markup of such parameters as: the presence of specific discourses, their ranks, positions in the linear sequence of discourses. (shrink)

In this essay I propose that what design principles in systems biology and systems neuroscience do is to present abstract characterizations of mechanisms, and thereby facilitate mechanistic explanation. To show this, one design principle in systems neuroscience, i.e., the multilayer perceptron, is examined. However, Braillard contends that design principles provide a sort of non-mechanistic explanation due to two related reasons: they are very general and describe non-causal dependence relationships. In response to this, I argue that, on the one hand, (...) all mechanisms are more or less general, and on the other, many design principles are causal systems. (shrink)

This review article discusses Andrzej Bielecki’s book _Models of Neurons and Perceptrons: Selected Problems and Challenges_, as published by Springer International Publishing. This work exemplifies “philosophy in science” by adopting a broad, multidisciplinary perspective for the issues related to the simulation of neurons and neural networks, and the author has addressed many of the important philosophical assumptions that are entangled in this area of modeling. Bielecki also raises several important methodological issues about modeling. This book is recommended for any philosophers (...) who wish to learn more about the current state of neural modeling and find inspiration for a deeper philosophical reflection on the subject. (shrink)

Online social networks are highly dynamic and sparse. One of the main problems in analyzing these networks is the problem of predicting the existence of links between users on these networks: the link prediction problem. Many studies have been conducted to predict links using a variety of techniques like the decision tree and the logistic regression approaches. In this work, we will illustrate the use of the rough set theory in predicting links over the Facebook social network based on homophilic (...) features. Other supervised learning algorithms are also employed in our experiments and compared with the rough set classifier, such as naive Bayes, J48 decision tree, support vector machine, logistic regression, and multilayer perceptron neural network. Moreover, we studied the influence of the “common groups” and “common page likes” homophilic features on predicting friendship between users of Facebook, and also studied the effect of using the Jaccard coefficient in measuring the similarity between users’ homophilic attributes compared with using the overlap coefficient. We conducted our experiments on two different datasets obtained from the Facebook online social network, where users in each dataset live within the same geographical region. The results showed that the rough set classifier significantly outperformed the other classifiers in all experiments. The results also demonstrated that the common groups and the common page likes features have a significant influence on predicting the friendship between users of Facebook. Finally, the results revealed that using the overlap coefficient homophilic features provided better results than that of the Jaccard coefficient features. (shrink)

In traditional 3D reconstruction methods, using a single view to predict the 3D structure of an object is a very difficult task. This research mainly discusses human pose recognition and estimation based on 3D multiview basketball sports dataset. The convolutional neural network framework used in this research is VGG11, and the basketball dataset Image Net is used for pretraining. This research uses some modules of the VGG11 network. For different feature fusion methods, different modules of the VGG11 network are used (...) as the feature extraction network. In order to be efficient in computing and processing, the multilayer perceptron in the network model is implemented by a one-dimensional convolutional network. The input is a randomly sampled point set, and after a layer of perceptron, it outputs a feature set of n × 16. Then, the feature set is sent to two network branches, one is to continue to use the perceptron method to generate the feature set of n × 1024, and the other network is used to extract the local features of points. After the RGB basketball sports picture passes through the semantic segmentation network, a picture containing the target object is obtained, and the picture is input to the constructed feature fusion network model. After feature extraction is performed on the RGB image and the depth image, respectively, the RGB feature, the local feature of the point cloud, and the global feature are spliced and fused to form a feature vector of N × 1152. There are three branches for this vector network, which, respectively, predict the object position, rotation, and confidence. Among them, the feature dimensionality reduction is realized by one-dimensional convolution, and the activation function is the ReLU function. After removing the feature mapping module, the accuracy of VC-CNN_v1 dropped by 0.33% and the accuracy of VC-CNN_v2 dropped by 0.55%. It can be seen from the research results that the addition of the feature mapping module improves the recognition effect of the network to a certain extent. (shrink)

Large language models in the form of chatbots very realistically imitate a dialogue as an omniscient interlocutor and therefore have become widespread. But even Google in its Gemini chatbot does not recommend trusting what the chatbot will write and asks to check its answers. In this review, various types of LLM errors such as the curse of inversion, number processing, etc. will be analyzed to identify their causes. Such an analysis led to the conclusion about the common causes of all (...) errors, which is that transformers do not have deep analogy, hierarchy of schemes and selectivity of content taken into account in the inference. But the most important conclusion is that transformers, like other neural networks, are built on the concept of processing the input signal, which creates a strong dependence on superficial noise and irrelevant information that the transformer’s attention layer cannot compensate for. The concept of neural networks was laid down in the 1950s by the idea of F. Rosenblatt’s perceptron and did not take into account the achievements of cognitive psychology that appeared later. According to the constructivist paradigm, the input word (or perception) is only a way to check the correctness of the constructed predictive model for possible situations. This is the cause of the biggest problem of transformers, called hallucinations. And its elimination is possible only by changing the architecture of the neural network, but not by increasing the amount of data in training. (shrink)

The frequency of cyberattacks has been rapidly increasing in recent times, which is a significant concern. These attacks exploit vulnerabilities present in the software components that constitute the targeted system. Consequently, the number of vulnerabilities within these software components serves as an indicator of the system’s level of security and trustworthiness. This paper compares the accuracy, trainability and stability to configuration parameters of several neural network architectures, namely Long Short-Term Memory, Multilayer Perceptron and Convolutional Neural Network. These architectures are (...) utilized for forecasting the number of software vulnerabilities within a specified timeframe for a specific software product. By evaluating these neural network models, our aim is to provide insights into their performance and effectiveness in vulnerability forecasting. (shrink)

The safety of the transmission lines maintains the stable and efficient operation of the smart grid. Therefore, it is very important and highly desirable to diagnose the health status of transmission lines by developing an efficient prediction model in the grid sensor network. However, the traditional methods have limitations caused by the characteristics of high dimensions, multimodality, nonlinearity, and heterogeneity of the data collected by sensors. In this paper, a novel model called LPR-MLP is proposed to predict the health status (...) of the power grid sensor network. The LPR-MLP model consists of two parts: local binary pattern, principal component analysis, and ReliefF are used to process image data and meteorological and mechanical data and the multilayer perceptron method is then applied to build the prediction model. The results obtained from extensive experiments on the real-world data collected from the online system of China Southern Power Grid demonstrate that this new LPR-MLP model can achieve higher prediction accuracy and precision of 86.31% and 85.3%, compared with four traditional methods. (shrink)

Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in real-time data streaming scenarios is a research area that has not yet been fully addressed. Nevertheless, much effort has been put into the adaption of complex deep learning (DL) models to streaming tasks by reducing the processing time. The design of the asynchronous dual-pipeline DL framework allows (...) making predictions of incoming instances and updating the model simultaneously, using two separate layers. The aim of this work is to assess the performance of different types of DL architectures for data streaming classification using this framework. We evaluate models such as multi-layer perceptrons, recurrent, convolutional and temporal convolutional neural networks over several time series datasets that are simulated as streams at different speeds. In addition, we evaluate how the different architectures react to concept drifts typically found in evolving data streams. The obtained results indicate that convolutional architectures achieve a higher performance in terms of accuracy and efficiency, but are also the most sensitive to concept drifts. (shrink)

Dragon boat sport is a traditional activity in China. In recent years, dragon boat sport has become more and more popular around the world. In order to face more challenges, it is urgent for athletes to enhance their own strength. Scientific training methods are particularly important for athletes, and accurate training data are the basis to support scientific training. Traditional mathematical statistic methods neither can sample signals accurately nor can they do real-time analysis and feedback the characteristics to each athlete. (...) In this paper, we use the wearable device with a triaxial accelerometer and heart rate sensor builtin to sample the speed signals and heart rate signals of athletes in various stages of men’s 1000m straight race. Based on the complex network theory, we regard the 23 dragon boat athletes in the dragon boat race as 23 nodes so as to establish a network with 23 nodes and reflect the importance of nodes by measuring the impact of node deletion on the results of the race. The neural network multilayer perceptron model is used for training to obtain the optimal combined value with speed and heart rate for each race stage. The optimal value will be used in the simulated race as the target value to verify if it can help to improve the training efficiency. Experimental results show that the optimal value obtained by this method has a positive effect on the results of the dragon boat race which is beneficial to sports training and tactics planning. (shrink)

Malware is a sophisticated, malicious, and sometimes unidentifiable application on the network. The classifying network traffic method using machine learning shows to perform well in detecting malware. In the literature, it is reported that this good performance can depend on a reduced set of network features. This study presents an empirical evaluation of two statistical methods of reduction and selection of features in an Android network traffic dataset using six supervised algorithms: Naïve Bayes, support vector machine, multilayer perceptron neural (...) network, decision tree, random forest, and K-nearest neighbors. The principal component analysis and logistic regression methods with p value were applied to select the most representative features related to the time properties of flows and features of bidirectional packets. The selected features were used to train the algorithms using binary and multiclass classification. For performance evaluation and comparison metrics, precision, recall, F-measure, accuracy, and area under the curve were used. The empirical results show that random forest obtains an average accuracy of 96% and an AUC-ROC of 0.98 in binary classification. For the case of multiclass classification, again random forest achieves an average accuracy of 87% and an AUC-ROC over 95%, exhibiting better performance than the other machine learning algorithms. In both experiments, the 13 most representative features of a mixed set of flow time properties and bidirectional network packets selected by LR were used. In the case of the other five classifiers, their results in terms of precision, recall, and accuracy, are competitive with those obtained in related works, which used a greater number of input features. Therefore, it is empirically evidenced that the proposed method for the selection of features, based on statistical techniques of reduction and extraction of attributes, allows improving the identification performance of malware traffic, discriminating it from the benign traffic of Android applications. (shrink)

This paper aims to offer a new view of the role of connectionist models in the study of human cognition through the conceptualization of the history of connectionism – from the simplest perceptrons to convolutional neural nets based on deep learning techniques, as well as through the interpretation of criticism coming from symbolic cognitive science. Namely, the connectionist approach in cognitive science was the target of sharp criticism from the symbolists, which on several occasions caused its marginalization and almost complete (...) abandonment of its assumptions in the study of cognition. Criticisms have mostly pointed to its explanatory inadequacy as a theory of cognition or to its biological implausibility as a theory of implementation, and critics often focused on specific shortcomings of some connectionist models and argued that they apply to connectionism in general. In this paper, we want to show that both types of critique are based on the assumption that the only valid explanations in cognitive science are instances of homuncular functionalism and that by removing this assumption and by adopting an alternative methodology – exploratory mechanistic strategy, we can reject most objections to connectionism as irrelevant, explain the progress of connectionist models despite their shortcomings and sketch the trajectory of their future development. By adopting mechanistic explanations and by criticizing functionalism, we will reject the objections of explanatory inadequacy, by characterizing connectionist models as generic rather than concrete mechanisms, we will reject the objections of biological implausibility, and by attributing the exploratory character to connectionist models we will show that practice of generalizing current to general failures of connectionism is unjustified. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:The Philosophic Foundations of Mimetic Theory and Cognitive Science(Including Artificial Intelligence)Jean-Pierre Dupuy (bio)In the mid 1970s I discovered at the same time cognitive science and mimetic theory. Being a philosopher with a scientific background, I immediately brought them together and tried to reconceptualize the latter in terms of the former. In a sense, I haven't stopped doing that in the last 45 years. That is why I feel fully (...) at home with the goals pursued by the organizers of this conference.I do not believe it is feasible or even desirable to operate the rapprochement between the two disciplines at a global level. The history of cognitive science is exceedingly involved, and the part played by artificial intelligence in it compared to the part played by the neurosciences has varied greatly over time.1 Only a piecemeal approach makes sense. I present here four short case studies that cover the whole period, from the beginnings in cybernetics to today's artificial intelligence (AI).In order to better situate these studies within a broader frame, I propose the diagram in Figure 1. To comment on it would require more time than available for my whole presentation. Let me just say the following. [End Page 1]It is essential to distinguish between two kinds of AI. The first to bear this name was launched by economist Herbert Simon and computer scientist Allan Newell at a Dartmouth conference in 1956. It was based on the premise that thinking is computing, with this computation bearing on sentences of a "language of thought" implementable in a digital computer. It turns out that this AI(1) was progressively substituted from the 1980s onward by an AI(2), which, to some extent, was a return to a fundamental result obtained by cybernetics in 1943. Neurophysiologist Warren McCulloch and mathematician Walter Pitts had constructed a mathematical model of a network of elementary calculators called "neurons" and explored its properties. The capacity to "think" was one of these. It was not situated at the elementary level, as was the case in AI(1), but it emerged at the collective level from the interactions between the neurons.This model was heavily criticized by the supporters of AI(1),2 and its first implementations, in the notorious "Perceptron" in particular (1957), were pitiful failures. However, the emergence of "second-order cybernetics" under the guidance of cybernetician Heinz von Foerster and the theory of complex, self-organizing systems that it helped develop, in cooperation and rivalry with similar efforts in the physical sciences, enabled the neural network model to come to a second life under different names: formal neurons, deep learning, big data, and the like. Together, they constitute AI(2).The following network of influences wouldn't have been possible without its stem, that is, the boxes containing the names of Kurt Gödel and Alan Turing. The former revolutionized logic by showing that reasoning about arithmetic and arithmetic are one and the same, insofar as it is possible to code in a 1-to-1 fashion propositions about integers (for instance, "7 is a prime number") by means of integers. The latter demonstrated that some mechanisms can self-transcend inasmuch as they generate an ensemble of outputs that cannot be defined mechanistically. Later, John von Neumann, who is credited along with Alan Turing with having invented the digital computer, would use this logical possibility to define complexity: A mechanism is complex if it is capable of generating one more complex than itself. The gate was open for the theories of complex, self-organizing systems to thrive and, by way of consequence, for AI(2) to emerge.fascination with modelsHerbert Simon (1916–2001), winner of the Nobel Prize in economics for his work on what he called "bounded rationality," is generally considered to be one [End Page 2] Click for larger view View full resolutionFigure 1.of the founders of artificial intelligence. Some cognitive scientists still rely on the computer program that he devised with Alan Newell to simulate the creative processes of human thought—a program aptly named "General Problem Solver." The title of one of his principal works, The Sciences of the... (shrink)

This paper introduces an advanced event detection model for legal intelligence, focusing on identifying event types in legal cases by examining trigger word candidates. It employs the DeBERTa pre-trained language model for encoding sentences into enriched word representations, supplemented by the Global Pointer neural network for initial scoring. The model further uses a graph convolutional network, conditional layer normalisation, and a convolutional neural network to extract features from these representations. A multilayer perceptron then determines the event type based on (...) these features and initial scores. Additionally, a dictionary-matching method revises the predicted event types, with adversarial training and a sentence-length mask employed to enhance model performance and address missing trigger words. The model’s effectiveness is proven through extensive experimentation, outperforming state-of-the-art baselines (including some large language models) and securing third prize in the event detection task at the Challenge of AI in Law (CAIL) 2022. The code of our model is available at https://github.com/1gst/DGGCCN/tree/main. (shrink)

Nowadays, online product reviews have been at the heart of the product assessment process for a company and its customers. They give feedback to a company on improving product quality, planning, and monitoring its business schemes in order to increase sale and gain more profit. They are also helpful for customers to select the right products in less effort and time. Most companies make spam reviews of products in order to increase the products sales and gain more profit. Detecting spam (...) product reviews is a challenging issue in NLP. Numerous machine learning approaches have attempted to detect and classify the product reviews as spam or nonspam. However, in order to improve the classification accuracy, this study has introduced an ensemble machine learning model that combines predictions from multilayer perceptron, K-Nearest Neighbour, and Random Forest and predicts the outcome of the review as spam or real, based on the majority vote of the contributing models. In order to accomplish the task of spam review classification, the proposed ensemble and other benchmark boosting approaches are tested with 25 statistical features extracted from mobile application reviews of Yelp Dataset. Then, three different selection techniques are exploited to diminish the feature space and filter out the top 10 optimal features. The effectiveness of the proposed ensemble, the individual models, and other benchmark boosting approaches is again evaluated with 10 optimal features in terms of classification accuracy. Experimental outcomes illustrate that the proposed ensemble model outperformed the individual classifiers and state-of-the-art boosting approaches like Generalized Boost Regression Model, Extreme Gradient Boost, and AdaBoost Regression Model in terms of classification accuracy. (shrink)

The amount of information that is produced on a daily basis in the financial markets is vast and complex; consequently, the development of systems that simplify decision-making is an essential endeavor. In this article, several intelligent systems are proposed and tested to predict the closing price of the IBEX 35 index using more than ten years of historical data and five distinct architectures for neural networks. A multi-layer perceptron was the first step, followed by a simple recurrent neural network, (...) a gated recurrent unit network and two long-short-term memory (LSTM) networks. The results of the analyses performed on these models have demonstrated a powerful capacity for prediction. Additionally, the findings of this research point to the fact that the application of intelligent systems can simplify the decision-making process in financial markets, which is a substantial advantage. Furthermore, by comparing the predicted outcome errors between the models, the LSTM presents the lowest error with a higher computational time in the training phase. The LSTM was able to accurately forecast the closing price of the day as well as the price for the following one and two days in advance. In conclusion, the empirical results demonstrated that these models could accurately predict financial data for trading purposes and that the application of intelligent systems, such as the LSTM network, represents a promising advancement in financial technology. (shrink)

Adaptive optics are techniques used for processing the spatial resolution of astronomical images taken from large ground-based telescopes. In this work, computational results are presented for a modified curvature sensor, the tomographic pupil image wavefront sensor, which measures the turbulence of the atmosphere, expressed in terms of an expansion over Zernike polynomials. Convolutional neural networks are presented as an alternative to the TPI-WFS reconstruction. This technique is a machine learning model of the family of artificial neural networks, which are widely (...) known for its performance as modeling and prediction technique in complex systems. Results obtained from the reconstruction of the networks are compared with the TPI-WFS reconstruction by estimating errors and optical measurements. The reconstructed wavefronts from both techniques are compared for wavefronts of 153 Zernike modes. For this case, a detailed comparison and grid search to find the most suitable neural network is performed, searching between multi-layer perceptron, CNN and recurrent networks topologies. In general, the best network was a CNN trained for TPI-WFS reconstruction, achieving better performance than the reconstruction software from TPI-WFS in most of the turbulent profiles, but the most significant improvements were found for higher turbulent profiles that have the lowest r0 values. (shrink)

One of the important measures of quality of education is the performance of students in academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and to improve their performance ahead of time using data mining techniques. In this paper, we developed a student performance prediction model that predicts the performance of high school students for the next semester for five courses. We modeled our prediction system as (...) a multi-label classification task and used support vector machine (SVM), Random Forest (RF), K-nearest Neighbors (KNN), and Multi-layer perceptron (MLP) as base-classifiers to train our model. We further improved the performance of the prediction model using a state-of-the-art partitioning scheme to divide the label space into smaller spaces and used Label Powerset (LP) transformation method to transform each labelset into a multi-class classification task. The proposed model achieved better performance in terms of different evaluation metrics when compared to other multi-label learning tasks such as binary relevance and classifier chains. (shrink)

In order to improve the accuracy and reliability of wireless location in NLOS environment, a wireless location algorithm based on artificial neural network is proposed for NLOS positioning error caused by non-line-of-sight propagation, such as occlusion and signal reflection. The mapping relationship between TOA and TDOA measurement data and coordinates is established. The connection weights of neural network are estimated as the state variables of nonlinear dynamic system. The multilayer perceptron network is trained by the real-time neural network training (...) algorithm based on extended Kalman. Combined with the statistical characteristics of NLOS error, the state component NLOS bias estimation is modified to realize TDOA data reconstruction. Simulation and experimental data analysis show that the algorithm can effectively weaken the influence of NLOS error. The localization method does not depend on the specific NLOS error distribution, nor does it need LOS and NLOS recognition. It can significantly improve the mobile positioning accuracy. (shrink)

The liver is the human body’s mandatory organ, but detecting liver disease at an early stage is very difficult due to the hiddenness of symptoms. Liver diseases may cause loss of energy or weakness when some irregularities in the working of the liver get visible. Cancer is one of the most common diseases of the liver and also the most fatal of all. Uncontrolled growth of harmful cells is developed inside the liver. If diagnosed late, it may cause death. Treatment (...) of liver diseases at an early stage is, therefore, an important issue as is designing a model to diagnose early disease. Firstly, an appropriate feature should be identified which plays a more significant part in the detection of liver cancer at an early stage. Therefore, it is essential to extract some essential features from thousands of unwanted features. So, these features will be mined using data mining and soft computing techniques. These techniques give optimized results that will be helpful in disease diagnosis at an early stage. In these techniques, we use feature selection methods to reduce the dataset’s feature, which include Filter, Wrapper, and Embedded methods. Different Regression algorithms are then applied to these methods individually to evaluate the result. Regression algorithms include Linear Regression, Ridge Regression, LASSO Regression, Support Vector Regression, Decision Tree Regression, Multilayer Perceptron Regression, and Random Forest Regression. Based on the accuracy and error rates generated by these Regression algorithms, we have evaluated our results. The result shows that Random Forest Regression with the Wrapper Method from all the deployed Regression techniques is the best and gives the highest R2-Score of 0.8923 and lowest MSE of 0.0618. (shrink)

Taking to heart Massaro's [(1988) Some criticisms of connectionist models of human performance, Journal of Memory and Language, 27, 213-234] criticism that multi-layer perceptrons are not appropriate for modeling human cognition because they are too powerful (i.e. they can simulate just about anything, which gives them little explanatory power), Regier develops the notion of constrained connectionism. The model that he discusses is a distributed network but with numerous constraints added that are (more or less) motivated by real psychophysical and neurophysical (...) constraints. His model learns static prepositions of spatial location such as in, above, to the left of, to the right of, under, etc., as well as dynamic prepositions such as through and the Russian iz-pod, meaning out from under. The network learns these prepositions by viewing a number of examples of them. Very importantly, this book tackles-and goes a long way towards resolving-the problem of the lack of negative exemplars (i.e. we are only very rarely told when something is not above something else), which should lead to overgeneralization, but does not. This book is a significant contribution to connectionist literature. (shrink)

According to a recent proposal, natural concepts are represented in an optimally designed similarity space, adhering to principles a skilled engineer would use for creatures with our perceptual and cognitive capacities. One key principle is that natural concepts should be easily learnable. While evidence exists for parts of this optimal design proposal, there has been no direct evidence linking naturalness to learning until now. This article presents results from a computational study on perceptual color space, demonstrating that naturalness indeed facilitates (...) learning. (shrink)