A shortage or backlog of inventory can easily occur due to the backward forecasting method typically used, which will affect the normal flow of funds in pharmacies. This paper proposes a replenishment decision model with back propagation neural network multivariate regression analysis methods. With the regular pattern between sales and individual variables, supplemented with the safety stock empirical formula, an accurate replenishment quantity can be obtained. In the case analysis, this paper takes the sales situation of (...) a pharmacy as an example and tests the accuracy and stability of the model. The results show that the model has good prediction accuracy which can be introduced into the intelligent pharmacy system and used in the replenishment of the intelligent pharmacy to prevent overstocking or a shortage of stock, thus improving the financial situation, reducing the manpower burden of typical retail pharmacy, and helping residents buy medicines. (shrink)

Pneumatic muscle actuators own excellent compliance and a high power-to-weight ratio and have been widely used in bionic robots and rehabilitated robots. However, the high nonlinear characteristics of PMAs due to inherent construction and pneumatic driving principle bring great challenges in applications acquired accurately modeling and controlling. To tackle the tricky problem, a single PMA mass setup is constructed, and a back propagation neural network is employed to identify the dynamics of the setup. An offline model (...) is built up using sampled data, and online modifications are performed to further improve the quality of the model. An adaptive controller based on BPNN is designed using gradient descent information of the built-up model. Experiments of identifying the PMA setup using BPNN and position tracking by adaptive BPNN controller are performed, and results demonstrate the good capacity in accurate controlling of the PMA setup. (shrink)

It was meaningful to predict the customers' decision-making behavior in the field of market. However, due to individual differences and complex, non-linear natures of the electroencephalogram signals, it was hard to classify the EEG signals and to predict customers' decisions by using traditional classification methods. To solve the aforementioned problems, a recurrent t-distributed stochastic neighbor embedding neural network was proposed in current study to classify the EEG signals in the designed brand extension paradigm and to predict the participants' (...) decisions. The recurrent t-SNE neural network contained two steps. In the first step, t-SNE algorithm was performed to extract features from EEG signals. Second, a recurrent neural network with long short-term memory layer, fully connected layer, and SoftMax layer was established to train the features, classify the EEG signals, as well as predict the cognitive performance. The proposed network could give a good prediction with accuracy around 87%. Its superior in prediction accuracy as compared to a recurrent principal component analysis network, a recurrent independent component correlation algorithm [independent component analysis ] network, a t-SNE support vector machine network, a t-SNE back propagation neural network, a deep LSTM neural network, and a convolutional neural network were also demonstrated. Moreover, the performance of the proposed network with different activated channels were also investigated and compared. The results showed that the proposed network could make a relatively good prediction with only 16 channels. The proposed network would become a potentially useful tool to help a company in making marketing decisions and to help uncover the neural mechanisms behind individuals' decision-making behavior with low cost and high efficiency. (shrink)

Correlation analyses of recent back‐propagation neural networks show that network results are due to imbalances in stimulus input. Conclusions concerning the effects of receptive field size, hemispheric specialization, and other issues of relevance to psychology cannot therefore be drawn until the dominating effects of low‐level correlations are removed. Statistical techniques for evaluating the stimulus materials for neural networks are introduced.

Parkinson's Disease (PD) is a long-term degenerative disorder of the central nervous system that mainly affects the motor system. The symptoms generally come on slowly over time. Early in the disease, the most obvious are shaking, rigidity, slowness of movement, and difficulty with walking. Doctors do not know what causes it and finds difficulty in early diagnosing the presence of Parkinson’s disease. An artificial neural network system with back propagation algorithm is presented in this paper for (...) helping doctors in identifying PD. Previous research with regards to predict the presence of the PD has shown accuracy rates up to 93% [1]; however, accuracy of prediction for small classes is reduced. The proposed design of the neural network system causes a significant increase of robustness. It is also has shown that networks recognition rates reached 100%. (shrink)

Human resource management risks are due to the failure of employer organization to use relevant human resources reasonably and can result in tangible or intangible waste of human resources and even risks; therefore, constructing a practical early warning model of human resource management risk is extremely important for early risk prediction. The back propagation neural network is an information analysis and processing system formed by using the error back propagation algorithm to simulate the (...) class='Hi'>neural function and structure of the human brain, which can handle complex and changeable things that do not have an obvious linear relationship between output results and input factors, so as to find the objective connection between the two. Based on the summary and analysis of previous research works, this article expounded the research status and significance of early warning for human resource management risks, elaborated the development background, current status, and future challenges of the BP neural network, introduced the method and principle of the BP neural network’s connection weight calculation and learning training, performed the risk inducement analysis, index system establishment, and network node selection of human resource management, constructed an early warning model of human resource management risk based on the BP neural network, conducted the risk warning model training and detection based on the BP neural network, and finally carried out a simulation and its result analysis. The study results show that the early warning model of human resource management risk based on the BP network is effective, and this trained and tested BP network risk warning model can be used to conduct early warning empirical research on human resource risks to prevent human resource risks, ensure enterprise’s benign operation, and at the same time play a role in supervision and promotion of market order rectification. (shrink)

Gross domestic product can well reflect the development of the economy, and predicting GDP can help better grasp the future economic trends. In this article, three different neural network models, the genetic algorithm – back-propagation neural network model, the particle swarm optimization – Elman neural network model, and the bat algorithm – long short-term memory model, were analyzed based on neural networks. The GDP data of Sichuan province from 1992 to 2020 (...) were collected to compare the performance of the three models in predicting GDP. It was found that the mean absolute percentage error values of the three models were 0.0578, 0.0236, and 0.0654, respectively; the root-mean-square error values were 0.0287, 0.0166, and 0.0465, respectively; and the PSO-Elman NN model had the best performance in GDP prediction. The experimental results demonstrate that neural networks were reliable in predicting GDP and can be used for further applications in practice. (shrink)

This research aims to evaluate the calculation accuracy and efficiency of the artificial neural network-based important sampling method on reliability of structures such as drum brakes. The finite element analysis result is used to establish the ANN sample in ANN-based reliability analysis methods. Because the process of FEA is time-consuming, the ANN sample size has a very important influence on the calculation efficiency. Two types of ANNs used in this study are the radial basis function neural (...) class='Hi'>network and back propagation neural network. RBF-IS and BP-IS methods are used to conduct reliability analysis on training samples of three different sizes, and the results are compared with several reliability analysis methods based on ANNs. The results show that the probability of failure of the RBF-IS method is closer to that of the Monte-Carlo simulation method than those of other methods. In addition, the RBF-IS method has better calculation efficiency than the other methods considered in this study. This research demonstrates that the RBF-IS method is well suited to structure reliability problems. (shrink)

This study combines the discovery methods and training of innovative talents, China’s requirements for improving talent training capabilities, and analyses the relationship between the number of professional enrollments in colleges and universities and the demand for skills in specific places. The research learns the characteristics and training models of innovative talents, deep learning, neural networks, and related concepts of the seasonal difference Autoregressive Moving Average Model. These concepts are used to propose seasonal autoregressive integrated moving average back (...) class='Hi'>propagation. Firstly, the SARIMA-BP artificially sets the weight parameter values and analyzes the model’s convergence speed, superiority, and versatility. Then, particle swarm optimization algorithm is used to pre-process the model and test its independence. The accuracy of the model is checked to ensure its proper performance. Secondly, the model analyzes and predicts the relationship between the number of professional enrollments of 10 colleges and universities in a specific place and the talent demand of local related enterprises. Moreover, the established model is optimized and tested by wavelet denoising. Independent testing is done to ensure the best possible performance of the model. Finally, the weight value will not significantly affect the model’s versatility obtained by experiments. The prediction results of professional settings and corporate needs reveal that: there is a moderate correlation between professional locations and corporate needs; colleges and universities should train professional talents for local enterprises and eliminate the practical education concepts. (shrink)

For manufacturing enterprises to successfully enter the “Industry 4.0” era and establish advantages in the new wave of the Industrial Revolution, they must use Internet thinking to transform manufacturing enterprises and promote the in-depth integration of informatization and industrialization under the premise of managing and controlling risks, to achieve transformation and upgrading. Research on and management of the risks of manufacturing enterprises’ Internet strategic transformation directly affects the success or failure of enterprises’ transformation. This study constructed a risk evaluation model (...) for a manufacturing enterprise’s Internet strategic transformation based on the back propagation artificial neural network and conducted a case study on one enterprise. (shrink)

Previous neural network models of concept learning were mainly implemented with supervised learning schemes. However, studies of human conceptual memory have shown that concepts may be learned without a teacher who provides the category name to associate with exemplars. A modular neural network architecture that realizes concept acquisition through two functionally distinct operations, categorizing and naming, is proposed as an alternative. An unsupervised algorithm realizes the categorizing module by constructing representations of categories compatible with prototype theory. (...) The naming module associates category names to the output of the categorizing module in a supervised mode. In such a modular architecture, the interface between the modules can be conceived of as an “information relay” that encodes, constrains, and propagates important information. Five experiments were conducted to analyze the relationships among internal conceptual codes and simple conceptual and lexical development. The first two experiments show a prototype effect and illustrate some basic characteristics of the system. The third experiment presents a bottom‐up model of the narrowing down of children's early lexical categories that honors mutual exclusivity. The fourth experiment introduces top‐down constraints on conceptual coding. The fifth experiment exhibits how hierarchical relationships between concepts are learned by the architecture, and also demonstrates how a spectrum of conceptual expertise may gradually emerge as a consequence of experiencing more with certain categories than with others. (shrink)

Previous neural network models of concept learning were mainly implemented with supervised learning schemes. However, studies of human conceptual memory have shown that concepts may be learned without a teacher who provides the category name to associate with exemplars. A modular neural network architecture that realizes concept acquisition through two functionally distinct operations, categorizing and naming, is proposed as an alternative. An unsupervised algorithm realizes the categorizing module by constructing representations of categories compatible with prototype theory. (...) The naming module associates category names to the output of the categorizing module in a supervised mode. In such a modular architecture, the interface between the modules can be conceived of as an “information relay” that encodes, constrains, and propagates important information. Five experiments were conducted to analyze the relationships among internal conceptual codes and simple conceptual and lexical development. The first two experiments show a prototype effect and illustrate some basic characteristics of the system. The third experiment presents a bottom‐up model of the narrowing down of children's early lexical categories that honors mutual exclusivity. The fourth experiment introduces top‐down constraints on conceptual coding. The fifth experiment exhibits how hierarchical relationships between concepts are learned by the architecture, and also demonstrates how a spectrum of conceptual expertise may gradually emerge as a consequence of experiencing more with certain categories than with others. (shrink)

We describe and try to motivate our project to build systems using both a knowledge based and a neural network approach. These two approaches are used at different stages in the solution of a problem, instead of using knowledge bases exclusively on some problems, and neural nets exclusively on others. The knowledge base (KB) is defined first in a declarative, symbolic language that is easy to use. It is then compiled into an efficient neural network (...) (NN) representation, run, and the results from run time and (eventually) from learning are decompiled to a symbolic description of the knowledge contained in the network. After inspecting this recovered knowledge, a designer would be able to modify the KB and go through the whole cycle of compiling, running, and decompiling again. The central question with which this project is concerned is, therefore, How do we go from a KB to an NN, and back again? We are investigating this question by building tools consisting of a repertoire of language/translation/network types, and trying them on problems in a variety of domains. (shrink)

Speech recognition plays an important role in human–computer interaction. The higher the accuracy and efficiency of speech recognition are, the larger the improvement of human–computer interaction performance. This article briefly introduced the hidden Markov model -based English speech recognition algorithm and combined it with a back-propagation neural network to further improve the recognition accuracy and reduce the recognition time of English speech. Then, the BPNN-combined HMM algorithm was simulated and compared with the HMM algorithm and the (...) BPNN algorithm. The results showed that increasing the number of test samples increased the word error rate and recognition time of the three speech recognition algorithms, among which the word error rate and recognition time of the BPNN-combined HMM algorithm were the lowest. In conclusion, the BPNN-combined HMM can effectively recognize English speeches, which provides a valid reference for intelligent recognition of English speeches by computers. (shrink)

The study investigates the possibility of applying texture analysis (TA) for testing Duchenne Muscular Dystrophy (DMD) therapies. The work is based on the Golden Retriever Muscular Dystrophy (GRMD) canine model, in which 3 phases of canine growth and/or dystrophy development are identified: the first phase (0–4 months of age), the second phase (from over 4 to 6 months), and the third phase (from over 6 months to death). Two differentiation problems are posed: (i) the first phase vs. the second phase (...) and (ii) the second phase vs. the third phase. Textural features are derived from T2-weighted Magnetic Resonance Imaging (MRI) images. In total, 37 features provided by 8 different TA methods (statistical, filter-based, and model-based) have been tested. The work focuses on finding such textural features that evolve along with the dog’s growth. These features are indicated by means of statistical analyses and eliminated from further investigation, as they may disturb the correct assessment of response to treatment in dystrophy. The relative importance of each remaining feature is then assessed with the use of the Monte Carlo (MC) procedure. Furthermore, feature selection based on the MC procedure is employed to find the optimal subset of age-independent features. Finally, three classifiers are used for evaluating different sets of textural features: Adaptive Boosting (AB), back-propagation Neural Network (NN), and nonlinear Support Vector Machines (SVM). The best subsets of age-independent features ensure 80.0% and 78.5% of correctly identified phases of dystrophy progression, for the first (i) and second (ii) differentiation problem respectively. (shrink)

Ataxia is a kind of external characteristics when the human body has poor coordination and balance disorder, it often indicates diseases in certain parts of the body. Many internal factors may causing ataxia; currently, observed external characteristics, combined with Doctor’s personal clinical experience play main roles in diagnosing ataxia. In this situation, different kinds of diseases may be confused, leading to the delay in treatment and recovery. Modern high precision medical instruments would provide better accuracy but the economic cost is (...) a non-negligible factor. In this paper, novel non-contact sensing technique is used to detect and distinguish sensory ataxia and cerebellar ataxia. Firstly, Romberg’s test and gait analysis data are collected by the microwave sensing platform; then, after some preprocessing, some machine learning approaches have been applied to train the models. For Romberg’s test, time domain features are considered, the accuracy of all the three algorithms are higher than 96%; for gait detection, Principal Component Analysis is used for dimensionality reduction, and the accuracies of Back Propagation neural Network, Support Vector Machine, and Random Forest are 97.8, 98.9, and 91.1%, respectively. (shrink)

With the rapid expansion of Internet technology, this research aims to explore the teaching strategies of ceramic art for contemporary students. Based on deep learning, an automatic question answering system is established, new teaching strategies are analyzed, and the Internet is combined with the automatic QA system to help students solve problems encountered in the process of learning. Firstly, the related theories of DL and personalized learning are analyzed. Among DL-related theories, Back Propagation Neural Network, Convolutional (...) Neural Network, Long Short-Term Memory, and Gated Recurrent Unit are compared to implement a single model and a mixed model. Secondly, the collected student questions are selected and processed, and experimental parameters in different models are set for comparative experiments. Experiments reveal that the average accuracy and Mean Reciprocal Rank of traditional retrieval methods can only reach about 0.5. In the basic neural network, the average accuracy of LSTM and GRU structural models is about 0.81, which can achieve better results. Finally, the accuracy of the hybrid model can reach about 0.82, and the accuracy and MRR of the Bidirectional Gated Recurrent Unit Network-Attention model are 0.87 and 0.89, respectively, achieving the best results. The established DL model meets the requirements of the online automatic QA system, improves the teaching system, and helps students better understand and solve problems in the ceramic art courses. (shrink)

In recent years, neural networks have attracted much attention in the machine learning and the deep learning technologies. Bio-inspired functions and intelligence are also expected to process efficiently and improve existing technologies. In the visual pathway, the prominent features consist of nonlinear characteristics of squaring and rectification functions observed in the retinal and visual cortex networks, respectively. Further, adaptation is an important feature to activate the biological systems, efficiently. Recently, to overcome short-comings of the deep learning techniques, orthogonality for (...) the weights in the networks has been developed for the signal propagation and the efficient optimization of the learning. In this paper, bio-inspired asymmetric networks with nonlinear characteristics are proposed, which are derived from the retinal networks in the biological visual pathway. The asymmetric network proposed here was verified to detect the movement of the object, efficiently in our previous studies. This paper shows a new characteristic of the adaptive orthogonality in the asymmetric networks. First, it is shown that the asymmetric network with nonlinear characteristics is effective for generating orthogonality. Second, the proposed asymmetric network with Gabor filters is compared with the conventional energy model from the point of the orthogonality characteristics. Finally, the asymmetric networks with nonlinear characteristics can generate the extended orthogonal bases in independent subspaces, which are useful for classification and efficient learning. (shrink)

With the development of technology, news media and film and television media are spreading faster and faster, and at the same time, the spread of rumors is also accelerated. This article briefly describes the application of artificial intelligence in news media and film and television media using a back-propagation neural network algorithm to reform refutation of rumors in news media and film and television media, and compared it with K-means and support vector machine algorithms in simulation (...) experiments. The results showed that the BPNN-based rumor recognition model had better recognition performance and shorter recognition time; it was more accurate in recognizing Weibo texts that were complete and faster in recognizing bullet screen comments that were short; the BPNN-based rumor recognition model also had the lowest false detection cost and performed stably when being used in actual Weibo platform and bullet screen video website. (shrink)

The accurate positioning of target is an important link in robot technology. Based on machine learning algorithm, this study firstly analyzed the location positioning principle of binocular vision of robot, then extracted features of the target using speeded-up robust features (SURF) method, positioned the location using Back Propagation Neural Networks (BPNN) method, and tested the method through experiments. The experimental results showed that the feature extraction of SURF method was fast, about 0.2 s, and was less affected (...) by noise. It was found from the positioning results that the output position of the BPNN method was basically consistent with the actual position, and errors in X, Y and Z directions were very small, which could meet the positioning needs of the robot. The experimental results verify the effectiveness of machine learning method and provide some theoretical support for its further promotion and application in practice. (shrink)

The energy sector contributes approximately two-thirds of global greenhouse gas emissions. In this context, the sector must adapt to new supply and demand networks for all future energy sources. The ongoing transformation in the European energy field is driven by the ambition of the European Union to reach the climate objectives set for 2030. The main actions are increasing renewable energy production, adapting transition fuels like natural gas to reduce emissions, improving energy efficiency across all economic sectors, prioritizing building, transportation, (...) and industry, developing Carbon Capture and Storage technologies, and ensuring universal access to clean and affordable energy. The significant changes envisaged in the energy sector to increase renewable energy production and consumption require improved integration and more use of predictive tools to support stakeholders' decision-making processes. This article presents a case study to assess the performance of predictive models based on a Feed-Forward Neural Network architecture that employ Root Mean Squared Propagation as their optimization function in terms of choosing the most appropriate activation function for this kind of data input and output. The training and testing phases of the models use data about building energy consumption. The lowest training time and Root Mean Square Error values were similar for Rectified Linear Unit and Tanh activation functions. The model with the Rectified linear Unit activation function performed best. (shrink)

Traffic congestion is a common problem in many countries, especially in big cities. At present, China’s urban road traffic accidents occur frequently, the occurrence frequency is high, the accident causes traffic congestion, and accidents cause traffic congestion and vice versa. The occurrence of traffic accidents usually leads to the reduction of road traffic capacity and the formation of traffic bottlenecks, causing the traffic congestion. In this paper, the formation and propagation of traffic congestion are simulated by using the improved (...) medium traffic model, and the control strategy of congestion dissipation is studied. From the point of view of quantitative traffic congestion, the paper provides the fact that the simulation platform of urban traffic integration is constructed, and a feasible data analysis, learning, and parameter calibration method based on RBF neural network is proposed, which is used to determine the corresponding decision support system. The simulation results prove that the control strategy proposed in this paper is effective and feasible. According to the temporal and spatial evolution of the paper, we can see that the network has been improved on the whole. (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)

One of the great successes of the application of generalized quantifiers to natural language has been the ability to formulate robust semantic universals. When such a universal is attested, the question arises as to the source of the universal. In this paper, we explore the hypothesis that many semantic universals arise because expressions satisfying the universal are easier to learn than those that do not. While the idea that learnability explains universals is not new, explicit accounts of learning that can (...) make good on this hypothesis are few and far between. We propose a model of learning — back-propagation through a recurrent neural network — which can make good on this promise. In particular, we discuss the universals of monotonicity, quantity, and conservativity and perform computational experiments of training such a network to learn to verify quantifiers. Our results are able to explain monotonicity and quantity quite well. We suggest that conservativity may have a different source than the other universals. (shrink)

The annotated dataset is an essential requirement to develop an artificial intelligence system effectively and expect the generalization of the predictive models and to avoid overfitting. Lack of the training data is a big barrier so that AI systems can broaden in several domains which have no or missing training data. Building these datasets is a tedious and expensive task and depends on the domains and languages. This is especially a big challenge for low-resource languages. In this paper, we experiment (...) and evaluate many various approaches on sentiment analysis problems so that they can still obtain high performances under limited training data. This paper uses the preprocessing techniques to clean and normalize the data and generate the new samples from the limited training dataset based on many text augmentation techniques such as lexicon substitution, sentence shuffling, back translation, syntax-tree transformation, and embedding mixup. Several experiments have been performed for both well-known machine learning-based classifiers and deep learning models. We compare, analyze, and evaluate the results to indicate the advantage and disadvantage points of the techniques for each approach. The experimental results show that the data augmentation techniques enhance the accuracy of the predictive models; this promises that smart systems can be applied widely in several domains under limited training data. (shrink)

In order to improve the efficiency of the English translation, machine translation is gradually and widely used. This study briefly introduces the neural network algorithm for speech recognition. Long short-term memory (LSTM), instead of traditional recurrent neural network (RNN), was used as the encoding algorithm for the encoder, and RNN as the decoding algorithm for the decoder. Then, simulation experiments were carried out on the machine translation algorithm, and it was compared with two other machine translation (...) algorithms. The results showed that the back-propagation (BP) neural network had a lower word error rate and spent less recognition time than artificial recognition in recognizing the speech; the LSTM–RNN algorithm had a lower word error rate than BP–RNN and RNN–RNN algorithms in recognizing the test samples. In the actual speech translation test, as the length of speech increased, the LSTM–RNN algorithm had the least changes in the translation score and word error rate, and it had the highest translation score and the lowest word error rate under the same speech length. (shrink)

As development of the speech recognition system entirely depends upon the spoken language used for its development, and the very fact that speech technology is highly language dependent and reverse engineering is not possible, there is an utmost need to develop such systems for Indian languages. In this paper we present the implementation of a time delay neural network system (TDNN) in a modular fashion by exploiting the hidden structure of previously phonetic subcategory network for recognition of (...) Hindi consonants. For the present study we have selected all the Hindi phonemes for srecognition. A vocabulary of 207 Hindi words was designed for the task-specific environment and used as a database. For the recognition of phoneme, a three-layered network was constructed and the network was trained using the back propagation learning algorithm. Experiments were conducted to categorize the Hindi voiced, unvoiced stops, semi vowels, vowels, nasals and fricatives. A close observation of confusion matrix of Hindi stops revealed maximum confusion of retroflex stops with their non-retroflex counterparts. (shrink)

The paper develops a semi-formal model of learning which modifies the traditional paradigm of artificial neural networks, implementing deep learning by means of a key insight borrowed from the works of Marvin Minsky: the so-called Principle of Non-Compromise. The principle provides a learning mechanism which states that conflicts in the processing of data to be integrated are a mark of unreliability or irrelevance; hence, lower-level conflicts should lead to higher-level weight-adjustments. This internal mechanism augments the external mechanism of weight (...) adjustment by back-propagation, which is typical for the standard models of machine learning. The text is structured as follows: (§1) opens the discussion by providing an informal overview of real-world decision-making and learning; (§2) sketches a typology of decision architectures: the individualistic approach of classical decision theory, the general aggregation mechanism of social choice theory, the local aggregation mechanism of agent-based modeling, and the intermediate hierarchical model of Marvin Minsky's “Society of Mind”; (§3) sketches the general outline of ANIMA – a new model of decision-making and learning that borrows insights from Minsky's informal exposition; (§4) is the bulk of the paper; it provides a discussion of a toy exemplification of ANIMA which lets us see the Principle of Non-Compromise at work; (§5) lists some possible scenarios for the evolution of a model of this kind; (§6) is the closing section; it discusses some important differences between the way ANIMA was construed here and the typical formal rendering of learning by means of artificial neural networks and deep learning. (shrink)

Formal models of argumentation have been investigated in several areas, from multi-agent systems and artificial intelligence (AI) to decision making, philosophy and law. In artificial intelligence, logic-based models have been the standard for the representation of argumentative reasoning. More recently, the standard logic-based models have been shown equivalent to standard connectionist models. This has created a new line of research where (i) neural networks can be used as a parallel computational model for argumentation and (ii) neural networks can (...) be used to combine argumentation, quantitative reasoning and statistical learning. At the same time, non-standard logic models of argumentation started to emerge. In this paper, we propose a connectionist cognitive model of argumentation that accounts for both standard and non-standard forms of argumentation. The model is shown to be an adequate framework for dealing with standard and non-standard argumentation, including joint-attacks, argument support, ordered attacks, disjunctive attacks, meta-level attacks, self-defeating attacks, argument accrual and uncertainty. We show that the neural cognitive approach offers an adequate way of modelling all of these different aspects of argumentation. We have applied the framework to the modelling of a public prosecution charging decision as part of a real legal decision making case study containing many of the above aspects of argumentation. The results show that the model can be a useful tool in the analysis of legal decision making, including the analysis of what-if questions and the analysis of alternative conclusions. The approach opens up two new perspectives in the short-term: the use of neural networks for computing prevailing arguments efficiently through the propagation in parallel of neuronal activations, and the use of the same networks to evolve the structure of the argumentation network through learning (e.g. to learn the strength of arguments from data). (shrink)

. Fuzzy systems and artificial neural networks, as important components of soft-computation, can be applied together to model uncertainty. A composite block of the fuzzy system and the ANN shares a mutually beneficial association resulting in enhanced performance with smaller networks. It makes them suitable for application with time-varying multi-input multi-output channel modeling enabling such a system to track minute variations in propagation conditions. Here we propose a fuzzy neural system using a fuzzy time delay fully recurrent (...) neural network that has the capability to tackle time-varying inputs in fuzzified form and is used to model MIMO channels. The inference engine is constituted by novel FTDFRNN blocks which determine the decision boundaries and tracks in-phase and quadrature components of input signals encompassing stochastic behavior of the MIMO channel. The system shows significant improvement in performance compared to statistical and ANN approaches in terms of faster processing time, lower bit error rate margins and better precision while carrying out symbol recovery of transmitted data through severely faded MIMO channels. (shrink)

The claims that learning systems must build causal models and provide explanations of their inferences are not new, and advocate a cognitive functionalism for artificial intelligence. This view conflates the relationships between implicit and explicit knowledge representation. We present recent evidence that neural networks do engage in model building, which is implicit, and cannot be dissociated from the learning process.

The comorbidity of chronic pain and opioid addiction is a serious problem that has been growing with the practice of prescribing opioids for chronic pain. Neuroimaging research has shown that chronic pain and opioid dependence both affect brain structure and function, but this is the first study to evaluate the neurophysiological alterations in patients with comorbid chronic pain and addiction. Eighteen participants with chronic low back pain and opioid addiction were compared with eighteen age- and sex-matched healthy individuals in (...) a pain-induction fMRI task. Unified structural equation modeling (SEM) with Lagrange multiplier (LM) testing yielded a network model of pain processing for patient and control groups based on 19 a priori defined regions. Tests of differences between groups on specific regression parameters were determined on a path-by-path basis using z-tests corrected for the number of comparisons. Patients with the chronic pain and addiction comorbidity had increased connection strengths; many of these connections were interhemispheric and spanned regions involved in sensory, affective, and cognitive processes. The affected regions included those that are commonly altered in chronic pain or addiction alone, indicating that this comorbidity manifests with neurological symptoms of both disorders. Understanding the neural mechanisms involved in the comorbidity is crucial to finding a comprehensive treatment, rather than treating the symptoms individually. (shrink)

The last two decades have produced unprecedented successes in the fields of artificial intelligence and machine learning (ML), due almost entirely to advances in deep neural networks (DNNs). Deep hierarchical memory networks are not a novel concept in cognitive science and can be traced back more than a half century to Simon's early work on discrimination nets for simulating human expertise. The major difference between DNNs and the deep memory nets meant for explaining human cognition is that the (...) latter are symbolic networks meant to model the dynamics of human memory and learning. Cognition-inspired symbolic deep networks (SDNs) address several known issues with DNNs, including (1) learning efficiency, where a much larger number of training examples are required for DNNs than would be expected for a human; (2) catastrophic interference, where what is learned by a DNN gets unlearned when a new problem is presented; and (3) explainability, where there is no way to explain what is learned by a DNN. This paper explores whether SDNs can achieve similar classification accuracy performance to DNNs across several popular ML datasets and discusses the strengths and weaknesses of each approach. Simulations reveal that (1) SDNs provide similar accuracy to DNNs in most cases, (2) SDNs are far more efficient than DNNs, (3) SDNs are as robust as DNNs to irrelevant/noisy attributes in the data, and (4) SDNs are far more robust to catastrophic interference than DNNs. We conclude that SDNs offer a promising path toward human-level accuracy and efficiency in category learning. More generally, ML frameworks could stand to benefit from cognitively inspired approaches, borrowing more features and functionality from models meant to simulate and explain human learning. (shrink)

In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Make, Model, Type, Origin, DriveTrain, MSRP, Invoice, EngineSize, Cylinders, Horsepower, MPG_Highway, Weight, Wheelbase, Length. ANN was used in prediction of the number of miles per gallon when the car is driven in the city(MPG_City). The results showed that ANN model was able to predict MPG_City (...) with 97.50 % accuracy. The factor of DriveTrain has the most influence on MPG_City evaluation. Similar studies can be carried out for the evaluation of other characteristics of cars. (shrink)

In this article we present symmetric diffusion networks, a family of networks that instantiate the principles of continuous, stochastic, adaptive and interactive propagation of information. Using methods of Markovion diffusion theory, we formalize the activation dynamics of these networks and then show that they can be trained to reproduce entire multivariate probability distributions on their outputs using the contrastive Hebbion learning rule (CHL). We show that CHL performs gradient descent on an error function that captures differences between desired and (...) obtained continuous multivariate probability distributions. This allows the learning algorithm to go beyond expected values of output units and to approximate complete probability distributions on continuous multivariate activation spaces. We argue that learning continuous distributions is an important task underlying a variety of real‐life situations that were beyond the scope of previous connectionist networks. Deterministic networks, like back propagation, cannot learn this task because they are limited to learning average values of independent output units. Previous stochastic connectionist networks could learn probability distributions but they were limited to discrete variables. Simulations show that symmetric diffusion networks can be trained with the CHL rule to approximate discrete and continuous probability distributions of various types. (shrink)

In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Buying, Maint, Doors, Persons, Lug_boot, Safety, and Overall. ANN was used in forecasting car acceptability. The results showed that ANN model was able to predict the car acceptability with 99.12 %. The factor of Safety has the most influence on car acceptability evaluation. Comparative study (...) method is suitable for the evaluation of car acceptability forecasting, can also be extended to all other areas. (shrink)

The subject matter of this book is the mental lexicon, that is, the way in which the form and meaning of words is stored by speakers of specific languages. This book attempts to narrow the gap between the results of experimental neurology and the concerns of theoretical linguistics in the area of lexical semantics. The prime goal as regards linguistic theory is to show how matters of lexical organization can be analysed and discussed within a neurologically informed framework that is (...) both adaptable and constrained. It combines the perspectives of distributed network modelling and linguistic semantics, and draws upon the accruing evidence from neuroimaging studies as regards the cortical regions involved. It engages with a number of controversial current issues in both disciplines. The book is intended as a tool for linguists interested in psychological adequacy and the latest advances in cognitive science. It provides a principled means of distinguishing those semantic features required by a mental lexicon that have a direct bearing on grammar from those that do not. It will appeal to researchers in neurolinguistics and lexical semantics."--p. 4 of cover. (shrink)

Computer assisted theorem proving is an increasingly important part of mathematical methodology, as well as a long-standing topic in artificial intelligence (AI) research. However, the current generation of theorem proving software have limited functioning in terms of providing new proofs. Importantly, they are not able to discriminate interesting theorems and proofs from trivial ones. In order for computers to develop further in theorem proving, there would need to be a radical change in how the software functions. Recently, machine learning results (...) in solving mathematical tasks have shown early promise that deep artificial neural networks could learn symbolic mathematical processing. In this paper, I analyze the theoretical prospects of such neural networks in proving mathematical theorems. In particular, I focus on the question how such AI systems could be incorporated in practice to theorem proving and what consequences that could have. In the most optimistic scenario, this includes the possibility of autonomous automated theorem provers (AATP). Here I discuss whether such AI systems could, or should, become accepted as active agents in mathematical communities. (shrink)

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend
the following theses. (1) Many neural networks compute—they perform computations. (2) Some neural networks compute in a classical way.
Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks
compute in a non-classical way. (4) Yet other neural networks do not perform computations. Brains may well (...) fall into this last class. (shrink)

Chronic back pain (CBP) is a leading cause of disability and results in considerable socio-economic burdens worldwide. Although CBP patients are commonly diagnosed and treated with a focus on the ‘end organ dysfunction’ (i.e., peripheral nerve injuries or diseases), the evaluation of CBP remains flawed and problematic with great challenges. Given that the peripheral nerve injuries or diseases are insufficient to define the etiology of CBP in some cases, the evaluation of alterations in the central nervous system becomes particularly (...) necessary and important. With the development of advanced neuroimaging techniques, extensive studies have been carried out to identify the cortical abnormalities in CBP patients. Here, we provide a comprehensive overview on a series of novel findings from these neuroimaging studies to improve our understanding of the cortical abnormalities originated in the disease. First, CBP patients normally exhibit central sensitization to external painful stimuli, which is indexed by increased pain sensitivity and brain activations in pain-related brain regions. Second, long-term suffering from chronic pain leads to emotional disorders, cognitive impairments, and the abnormalities of the relevant brain networks among CBP patients. Third, CBP is associated with massive cortical reorganization, including structural, functional, and metabolic brain changes. Overall, a deep insight into the neural mechanisms underlying the development and outcome of CBP through more sophisticated neuroimaging investigations could not only improve our current understanding of the etiology of CBP but also facilitate the diagnosis and treatment of CBP based on precision medicine. (shrink)

The apparent very close similarity between the learning of the past tense by Adam and the Plunkett and Marchman model is exaggerated by several misleading comparisons--including arbitrary, unexplained changes in how graphs were plotted. The model's development differs from Adam's in three important ways: Children show a U-shaped sequence of development which does not depend on abrupt changes in input; U-shaped development in the simulation occurs only after an abrupt change in training regimen. Children overregularize vowel-change verbs more than no-change (...) verbs; the simulation overregularizes vowel-change verbs less often than no-change verbs. Children, including Adam, overregularize more than they irregularize; the simulation overregularized less than it irregularized. Interestingly, the RM model--widely criticized as being inadequate--does somewhat better, correctly overregularizing vowel-change verbs more often than no-change verbs, and overregularizing more often than it irregularizes. Although Plunkett and Marchman's (1993) state of the art model incorporated hidden layers and back-propagation, used a more realistic phonological coding scheme, and explored a broader range of parameters than Rumelhart and McClelland's model, their results are farther from psychological reality. It is unknown whether any connectionist model can mimic a child's performance without resorting to unrealistic exogenous changes in the training or input, but it is clear that adding a hidden-layer and back-propagation does not ensure a solution. (shrink)

Deep neural networks (DNNs) have found many useful applications in recent years. Of particular interest have been those instances where their successes imitate human cognition and many consider artificial intelligences to offer a lens for understanding human intelligence. Here, we criticize the underlying conflation between the predictive and explanatory power of DNNs by examining the goals of modeling.

Human decision making shows systematic simplifications and deviations from the tenets of rationality (‘heuristics’) that may lead to suboptimal decisional outcomes (‘cognitive biases’). There are currently three prevailing theoretical perspectives on the origin of heuristics and cognitive biases: a cognitive-psychological, an ecological and an evolutionary perspective. However, these perspectives are mainly descriptive and none of them provides an overall explanatory framework for the underlying mechanisms of cognitive biases. To enhance our understanding of cognitive heuristics and biases we propose a (...) class='Hi'>neural network framework for cognitive biases, which explains why our brain systematically tends to default to heuristic (‘Type 1’) decision making. We argue that many cognitive biases arise from intrinsic brain mechanisms that are fundamental for the working of biological neural networks. In order to substantiate our viewpoint, we discern and explain four basic neural network principles: (1) Association, (2) Compatibility (3) Retainment, and (4) Focus. These principles are inherent to (all) neural networks which were originally optimized to perform concrete biological, perceptual, and motor functions. They form the basis for our inclinations to associate and combine (unrelated) information, to prioritize information that is compatible with our present state (such as knowledge, opinions and expectations), to retain given information that sometimes could better be ignored, and to focus on dominant information while ignoring relevant information that is not directly activated. The supposed mechanisms are complementary and not mutually exclusive. For different cognitive biases they may all contribute in varying degrees to distortion of information. The present viewpoint not only complements the earlier three viewpoints, but also provides a unifying and binding framework for many cognitive bias phenomena. (shrink)

Deep neural networks are said to be opaque, impeding the development of safe and trustworthy artificial intelligence, but where this opacity stems from is less clear. What are the sufficient properties for neural network opacity? Here, I discuss five common properties of deep neural networks and two different kinds of opacity. Which of these properties are sufficient for what type of opacity? I show how each kind of opacity stems from only one of these five properties, (...) and then discuss to what extent the two kinds of opacity can be mitigated by explainability methods. (shrink)

Diabetes is one of the most common diseases worldwide where a cure is not found for it yet. Annually it cost a lot of money to care for people with diabetes. Thus the most important issue is the prediction to be very accurate and to use a reliable method for that. One of these methods is using artificial intelligence systems and in particular is the use of Artificial Neural Networks (ANN). So in this paper, we used artificial neural (...) networks to predict whether a person is diabetic or not. The criterion was to minimize the error function in neural network training using a neural network model. After training the ANN model, the average error function of the neural network was equal to 0.01 and the accuracy of the prediction of whether a person is diabetics or not was 87.3%. (shrink)

This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of (...) BiLSTM-CRF models and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an \ score of 93.27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an \ score of 78.24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems. (shrink)

As a type of evidence glass can be very useful contact trace material in a wide range of offences including burglaries and robberies, hit-and-run accidents, murders, assaults, ram-raids, criminal damage and thefts of and from motor vehicles. All of that offer the potential for glass fragments to be transferred from anything made of glass which breaks, to whoever or whatever was responsible. Variation in manufacture of glass allows considerable discrimination even with tiny fragments. In this study, we worked glass classification (...) and testing of artificial neural network model created by the JustNN. The aim of the study is help investigator in identifying the type of glass found in arena of the crime. The Neural Network model was trained and validated using the type of glass dataset. The accuracy of model in predicting the type of glass reached 96.7%. Thus neural network is suitable for predicating type of glasses. (shrink)