The application of recycled aggregate as a sustainable material in construction projects is considered a promising approach to decrease the carbon footprint of concrete structures. Prediction of compressive strength of environmentally friendly concrete containing recycled aggregate is important for understanding sustainable structures’ concrete behaviour. In this research, the capability of the deep learning neural network approach is examined on the simulation of CS of EF concrete. The developed approach is compared to the well-known artificial intelligence approaches named multivariate (...) adaptive regression spline, extreme learning machines, and random forests. The dataset was divided into three scenarios 70%-30%, 80%-20%, and 90%-10% for training/testing to explore the impact of data division percentage on the capacity of the developed AI model. Extreme gradient boosting was integrated with the developed AI models to select the influencing variables on the CS prediction. Several statistical measures and graphical methods were generated to evaluate the efficiency of the presented models. In this regard, the results confirmed that the DLNN model attained the highest value of prediction performance with minimal root mean squared error. The study revealed that the highest prediction performance could be attained by increasing the number of variables in the prediction problem and using 90%-10% data division. The results demonstrated the robustness of the DLNN model over the other AI models in handling the complex behaviour of concrete. Due to the high accuracy of the DLNN model, the developed method can be used as a practical approach for future use of CS prediction of EF concrete. (shrink)

Recent events have highlighted large-scale systemic racial disparities in U.S. criminal justice based on race and other demographic characteristics. Although criminological datasets are used to study and document the extent of such disparities, they often lack key information, including arrestees’ racial identification. As AI technologies are increasingly used by criminal justice agencies to make predictions about outcomes in bail, policing, and other decision-making, a growing literature suggests that the current implementation of these systems may perpetuate racial inequalities. In this paper, (...) we argue that AI technologies should be investigated to understand how they recognize racial categories and whether they can be harnessed to fill missing race data. By bridging this gap, we can work towards better understanding racial inequalities in a wide range of contexts, most notably criminal justice. Using a multidisciplinary perspective, we rethink the design and methodology used in facial processing technology (FPT) based on supervised deep learning model (DLM) image classification. By modifying standard FPT pipelines to tackle multiple sources of DLM bias, we propose an experimental methodology based on ethical AI principles to generate binary (Black and White) racial categories using mugshots. We go beyond simply reporting DLM accuracies and address fundamental issues such as generalizability and interpretability by using a “self-auditing” approach. First, we evaluate the inference performances of 42 fine-tuned DLMs using unseen test images from the same dataset but subject to varying data augmentations. Next, to interpret and validate our methodological approach, we apply gradient-based saliency maps to assess the consistency of facial region relevance and attribution. Finally, drawing upon insights from three areas (computer science, sociology, and law), we investigate the efficacy of our DLM-based method as a tool for detecting racial inequalities in criminal justice. (shrink)

Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of symbolic regression. Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are underexplored. We propose a framework that leverages deep learning for symbolic regression via a simple idea: use a large model to search the space of small models. Specifically, we use a recurrent neural network to emit a (...) distribution over tractable mathematical expressions and employ a novel risk-seeking policy gradient to train the network to generate better-fitting expressions. Our algorithm outperforms several baseline methods (including Eureqa, the gold standard for symbolic regression) in its ability to exactly recover symbolic expressions on a series of benchmark problems, both with and without added noise. More broadly, our contributions include a framework that can be applied to optimize hierarchical, variable-length objects under a blackbox performance metric, with the ability to incorporate constraints in situ, and a risk-seeking policy gradient formulation that optimizes for best-case performance instead of expected performance. (shrink)

Speech recognition technology has played an indispensable role in realizing human-computer intelligent interaction. However, most of the current Chinese speech recognition systems are provided online or offline models with low accuracy and poor performance. To improve the performance of offline Chinese speech recognition, we propose a hybrid acoustic model of deep convolutional neural network, long short-term memory, and deep neural network. This model utilizes DCNN to reduce frequency variation and adds a batch normalization layer after its convolutional layer (...) to ensure the stability of data distribution, and then use LSTM to effectively solve the gradient vanishing problem. Finally, the fully connected structure of DNN is utilized to efficiently map the input features into a separable space, which is helpful for data classification. Therefore, leveraging the strengths of DCNN, LSTM, and DNN by combining them into a unified architecture can effectively improve speech recognition performance. Our model was tested on the open Chinese speech database THCHS-30 released by the Center for Speech and Language Technology of Tsinghua University, and it was concluded that the DLD model with 3 layers of LSTM and 3 layers of DNN had the best performance, reaching 13.49% of words error rate. (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)

In face recognition systems, highly robust facial feature representation and good classification algorithm performance can affect the effect of face recognition under unrestricted conditions. To explore the anti-interference performance of convolutional neural network reconstructed by deep learning framework in face image feature extraction and recognition, in the paper, first, the inception structure in the GoogleNet network and the residual error in the ResNet network structure are combined to construct a new deep reconstruction network algorithm, with the random (...) gradient descent and triplet loss functions as the model optimizer and classifier, respectively, and it is applied to the face recognition in Labeled Faces in the Wild face database. Then, the portrait pyramid segmentation and local feature point segmentation are applied to extract the features of face images, and the matching of face feature points is achieved using Euclidean distance and joint Bayesian method. Finally, Matlab software is used to simulate the algorithm proposed in this paper and compare it with other algorithms. The results show that the proposed algorithm has the best face recognition effect when the learning rate is 0.0004, the attenuation coefficient is 0.0001, the training method is SGD, and dropout is 0.1, and the algorithm proposed in this paper has the largest mean average precision compared to other CNN algorithms. The correct rate of face feature matching of the algorithm proposed in this paper is 84.72%, which is higher than LetNet-5, VGG-16, and VGG-19 algorithms, the correct rates of which are 6.94%, 2.5%, and 1.11%, respectively, but lower than GoogleNet, AlexNet, and ResNet algorithms. At the same time, the algorithm proposed in this paper has a faster matching time and a higher correct matching rate than the joint Bayesian method, indicating that the deep reconstruction network algorithm proposed in this paper can be used in face image recognition, FE, and matching, and it has strong anti-interference. (shrink)

Learning a deep structure representation for complex information networks is a vital research area, and assessing the quality of stereoscopic images or videos is challenging due to complex 3D quality factors. In this paper, we explore how to extract effective features to enhance the prediction accuracy of perceptual quality assessment. Inspired by the structure representation of the human visual system and the machine learning technique, we propose a no-reference quality assessment scheme for stereoscopic images. More specifically, the (...) statistical features of the gradient magnitude and Laplacian of Gaussian responses are extracted to form binocular quality-predictive features. After feature extraction, these features of distorted stereoscopic image and its human perceptual score are used to construct a statistical regression model with the machine learning technique. Experimental results on the benchmark databases show that the proposed model generates image quality prediction well correlated with the human visual perception and delivers highly competitive performance with the typical and representative methods. The proposed scheme can be further applied to the real-world applications on video broadcasting and 3D multimedia industry. (shrink)

One of the great challenges in word learning is that words are typically uttered in a context with many potential referents. Children's tendency to associate novel words with novel referents, which is taken to reflect a mutual exclusivity (ME) bias, forms a useful disambiguation mechanism. We study semantic learning in pragmatic agents—combining the Rational Speech Act model with gradient‐based learning—and explore the conditions under which such agents show an ME bias. This approach provides a framework for investigating (...) a pragmatic account of the ME bias in humans but also for building artificial agents that display an ME bias. A series of analyses demonstrates striking parallels between our model and human word learning regarding several aspects relevant to the ME bias phenomenon: online inference, long‐term learning, and developmental effects. By testing different implementations, we find that two components, pragmatic online inference and incremental collection of evidence for one‐to‐one correspondences between words and referents, play an important role in modeling the developmental trajectory of the ME bias. Finally, we outline an extension of our model to a deep neural network architecture that can process more naturalistic visual and linguistic input. Until now, in contrast to children, deep neural networks have needed indirect access to (supposed to be novel) test inputs during training to display an ME bias. Our model is the first one to do so without using this manipulation. (shrink)

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

Robustness is a significant constraint in machine learning models. The performance of the algorithms must not deteriorate when training and testing with slightly different data. Deep neural network models achieve awe-inspiring results in a wide range of applications of computer vision. Still, in the presence of noise or region occlusion, some models exhibit inaccurate performance even with data handled in training. Besides, some experiments suggest deep learning models sometimes use incorrect parts of the input information to (...) perform inference. Active image augmentation is an augmentation method that uses interpretability methods to augment the training data and improve its robustness to face the described problems. Although ADA presented interesting results, its original version only used the vanilla backpropagation interpretability to train the U-Net model. In this work, we propose an extensive experimental analysis of the interpretability method’s impact on ADA. We use five interpretability methods: vanilla backpropagation, guided backpropagation, gradient-weighted class activation mapping, guided GradCam and InputXGradient. The results show that all methods achieve similar performance at the ending of training, but when combining ADA with GradCam, the U-Net model presented an impressive fast convergence. (shrink)

In this paper, we study the face recognition and emotion recognition algorithms to monitor the emotions of preschool children. For previous emotion recognition focusing on faces, we propose to obtain more comprehensive information from faces, gestures, and contexts. Using the deep learning approach, we design a more lightweight network structure to reduce the number of parameters and save computational resources. There are not only innovations in applications, but also algorithmic enhancements. And face annotation is performed on the dataset, (...) while a hierarchical sampling method is designed to alleviate the data imbalance phenomenon that exists in the dataset. A new feature descriptor, called “oriented gradient histogram from three orthogonal planes,” is proposed to characterize facial appearance variations. A new efficient geometric feature is also proposed to capture facial contour variations, and the role of audio methods in emotion recognition is explored. Multifeature fusion can be used to optimally combine different features. The experimental results show that the method is very effective compared to other recent methods in dealing with facial expression recognition problems about videos in both laboratory-controlled environments and outdoor environments. The method performed experiments on expression detection in a facial expression database. The experimental results are compared with data from previous studies and demonstrate the effectiveness of the proposed new method. (shrink)

Knowing the level of quality from which the context is no longer valuable in a Context-Aware Data Mining (CADM) system is an important information. The main goal of this research is to study the variations of the predictions in case of different levels of noise and missing context data in practical scenarios for predicting soil moisture. The research has been performed on two locations from the Transylvanian Plain, Romania and two locations from Canada. The values predicted for the soil moisture (...) were compared in mixed scenarios that vary the quantity of noise and missing context data. The studied behavior was performed using Deep Learning, Decision Tree and Gradient Boosted Tree machine learning algorithms. It has been shown that when using the air temperature as context for predicting soil moisture, variations of noise and missing data do not influence the results proportionally with the levels of noise and missing data applied. Also, Gradient Boosted Tree algorithm proves to be the best algorithm from the ones studied, to be considered when predicting soil moisture with the CADM approach. (shrink)

Philosophers have recently focused on critical, epistemological challenges that arise from the opacity of deep neural networks. One might conclude from this literature that doing good science with opaque models is exceptionally challenging, if not impossible. Yet, this is hard to square with the recent boom in optimism for AI in science alongside a flood of recent scientific breakthroughs driven by AI methods. In this paper, I argue that the disconnect between philosophical pessimism and scientific optimism is driven by (...) a failure to examine how AI is actually used in science. I show that, in order to understand the epistemic justification for AI-powered breakthroughs, philosophers must examine the role played by deep learning as part of a wider process of discovery. The philosophical distinction between the 'context of discovery' and the 'context of justification' is helpful in this regard. I demonstrate the importance of attending to this distinction with two cases drawn from the scientific literature, and show that epistemic opacity need not diminish AI's capacity to lead scientists to significant and justifiable breakthroughs. (shrink)

Much has been written about the escalating intolerance of worldviews other than one's own. Reasoned arguments based on facts and data seem to have little impact in our increasingly post-truth culture dominated by social media, fake news, tribalism, and identity politics. Recent advances in the study of human cognition, however, offer insights on how to counter these troubling social trends. In this book, psychologist Jon F. Wergin calls upon recent research in learning theory, social psychology, politics, and the arts (...) to show how a deep learning mindset can be developed in both oneself and others. Deep learning is an acceptance that our understanding of the world around us is only temporary and is subject to constant scrutiny. Someone who is committed to learning deeply does not simply react to experiences, but engages fully with that experience, knowing that the inevitable disquietude is what leads to efficacy in the world. (shrink)

The application of deep learning methods to problems in natural language processing has generated significant progress across a wide range of natural language processing tasks. For some of these applications, deep learning models now approach or surpass human performance. While the success of this approach has transformed the engineering methods of machine learning in artificial intelligence, the significance of these achievements for the modelling of human learning and representation remains unclear. Deep Learning (...) and Linguistic Representation looks at the application of a variety of deep learning systems to several cognitively interesting NLP tasks. It also considers the extent to which this work illuminates our understanding of the way in which humans acquire and represent linguistic knowledge. Key Features: combines an introduction to deep learning in AI and NLP with current research on Deep Neural Networks in computational linguistics. is self-contained and suitable for teaching in computer science, AI, and cognitive science courses; it does not assume extensive technical training in these areas. provides a compact guide to work on state of the art systems that are producing a revolution across a range of difficult natural language tasks. (shrink)

Deep learning is currently the most prominent and widely successful method in artificial intelligence. Despite having played an active role in earlier artificial intelligence and neural network research, philosophers have been largely silent on this technology so far. This is remarkable, given that deep learning neural networks have blown past predicted upper limits on artificial intelligence performance—recognizing complex objects in natural photographs and defeating world champions in strategy games as complex as Go and chess—yet there remains (...) no universally accepted explanation as to why they work so well. This article provides an introduction to these networks as well as an opinionated guidebook on the philosophical significance of their structure and achievements. It argues that deep learning neural networks differ importantly in their structure and mathematical properties from the shallower neural networks that were the subject of so much philosophical reflection in the 1980s and 1990s. The article then explores several different explanations for their success and ends by proposing three areas of inquiry that would benefit from future engagement by philosophers of mind and science. (shrink)

In recent years, the family of algorithms collected under the term ``deep learning'' has revolutionized artificial intelligence, enabling machines to reach human-like performances in many complex cognitive tasks. Although deep learning models are grounded in the connectionist paradigm, their recent advances were basically developed with engineering goals in mind. Despite of their applied focus, deep learning models eventually seem fruitful for cognitive purposes. This can be thought as a kind of biological exaptation, where a (...) physiological structure becomes applicable for a function different from that for which it was selected. In this paper, it will be argued that it is time for cognitive science to seriously come to terms with deep learning, and we try to spell out the reasons why this is the case. First, the path of the evolution of deep learning from the connectionist project is traced, demonstrating the remarkable continuity, and the differences as well. Then, it will be considered how deep learning models can be useful for many cognitive topics, especially those where it has achieved performance comparable to humans, from perception to language. It will be maintained that deep learning poses questions that cognitive sciences should try to answer. One of such questions is the reasons why deep convolutional models that are disembodied, inactive, unaware of context, and static, are by far the closest to the patterns of activation in the brain visual system. (shrink)

This book provides a framework for thinking about foundational philosophical questions surrounding machine learning as an approach to artificial intelligence. Specifically, it links recent breakthroughs in deep learning to classical empiricist philosophy of mind. In recent assessments of deep learning's current capabilities and future potential, prominent scientists have cited historical figures from the perennial philosophical debate between nativism and empiricism, which primarily concerns the origins of abstract knowledge. These empiricists were generally faculty psychologists; that is, (...) they argued that the active engagement of general psychological faculties-such as perception, memory, imagination, attention, and empathy-enables rational agents to extract abstract knowledge from sensory experience. This book explains a number of recent attempts to model roles attributed to these faculties in deep neural network based artificial agents by appeal to the faculty psychology of philosophers such as Aristotle, Ibn Sina (Avicenna), John Locke David Hume, William James, and Sophie de Grouchy. It illustrates the utility of this interdisciplinary connection by showing how it can provide benefits to both philosophy and computer science: computer scientists can continue to mine the history of philosophy for ideas and aspirational targets to hit on the way to more robustly rational artificial agents, and philosophers can see how some of the historical empiricists' most ambitious speculations can be realized in specific computational systems. (shrink)

Accurate and reliable prediction of Perfobond Rib Shear Strength Connector is considered as a major issue in the structural engineering sector. Besides, selecting the most significant variables that have a major influence on PRSC in every important step for attaining economic and more accurate predictive models, this study investigates the capacity of deep learning neural network for shear strength prediction of PRSC. The proposed DLNN model is validated against support vector regression, artificial neural network, and M5 tree model. (...) In the second scenario, a comparable AI model hybridized with genetic algorithm as a robust bioinspired optimization approach for optimizing the related predictors for the PRSC is proposed. Hybridizing AI models with GA as a selector tool is an attempt to acquire the best accuracy of predictions with the fewest possible related parameters. In accordance with quantitative analysis, it can be observed that the GA-DLNN models required only 7 input parameters and yielded the best prediction accuracy with highest correlation coefficient and lowest value root mean square error. However, the other comparable models such as GA-M5Tree, GA-ANN, and GA-SVR required 10 input parameters to obtain a relatively acceptable level of accuracy. Employing GA as a feature parameter selection technique improves the precision of almost all hybrid models by optimally removing redundant variables which decrease the efficiency of the model. (shrink)

Responsible innovation in artificial intelligence calls for public deliberation: well-informed “deep democratic” debate that involves actors from the public, private, and civil society sectors in joint efforts to critically address the goals and means of AI. Adopting such an approach constitutes a challenge, however, due to the opacity of AI and strong knowledge boundaries between experts and citizens. This undermines trust in AI and undercuts key conditions for deliberation. We approach this challenge as a problem of situating the knowledge (...) of actors from the AI industry within a deliberative system. We develop a new framework of responsibilities for AI innovation as well as a deliberative governance approach for enacting these responsibilities. In elucidating this approach, we show how actors from the AI industry can most effectively engage with experts and nonexperts in different social venues to facilitate well-informed judgments on opaque AI systems and thus effectuate their democratic governance. (shrink)

With the rapid growth of informatics systems’ technology in this modern age, the Internet of Things (IoT) has become more valuable and vital to everyday life in many ways. IoT applications are now more popular than they used to be due to the availability of many gadgets that work as IoT enablers, including smartwatches, smartphones, security cameras, and smart sensors. However, the insecure nature of IoT devices has led to several difficulties, one of which is distributed denial-of-service (DDoS) attacks. IoT (...) systems have several security limitations due to their disreputability characteristics, like dynamic communication between IoT devices. The dynamic communications resulted from the limited resources of these devices, such as their data storage and processing units. Recently, many attempts have been made to develop intelligent models to protect IoT networks against DDoS attacks. The main ongoing research issue is developing a model capable of protecting the network from DDoS attacks that is sensitive to various classes of DDoS and can recognize legitimate traffic to avoid false alarms. Subsequently, this study proposes combining three deep learning algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM)-RNN, and convolutional neural network (CNN), to build a bidirectional CNN-BiLSTM DDoS detection model. The RNN, CNN, LSTM, and CNN-BiLSTM are implemented and tested to determine the most effective model against DDoS attacks that can accurately detect and distinguish DDoS from legitimate traffic. The intrusion detection evaluation dataset (CICIDS2017) is used to provide more realistic detection. The CICIDS2017 dataset includes benign and up-to-date examples of typical attacks, closely matching real-world data of Packet Capture. The four models are tested and assessed using Confusion Metrix against four commonly used criteria: accuracy, precision, recall, and F-measure. The performance of the models is quite effective as they obtain an accuracy rate of around 99.00%, except for the CNN model, which achieves an accuracy of 98.82%. The CNN-BiLSTM achieves the best accuracy of 99.76% and precision of 98.90%. (shrink)

We claim that scientists working with deep learning (DL) models exhibit a form of pragmatic understanding that is not reducible to or dependent on explanation. This pragmatic understanding comprises a set of learned methodological principles that underlie DL model design-choices and secure their reliability. We illustrate this action-oriented pragmatic understanding with a case study of AlphaFold2, highlighting the interplay between background knowledge of a problem and methodological choices involving techniques for constraining how a model learns from data. Building (...) successful models requires pragmatic understanding to apply modelling strategies that encourage the model to learn data patterns that will facilitate reliable generalisation. (shrink)

In this paper we analyse the conditions for attributing to AI autonomous systems the ontological status of “artificial moral agents”, in the context of the “distributed responsibility” between humans and machines in Machine Ethics (ME). In order to address the fundamental issue in ME of the unavoidable “opacity” of their decisions with ethical/legal relevance, we start from the neuroethical evidence in cognitive science. In humans, the “transparency” and then the “ethical accountability” of their actions as responsible moral agents is not (...) in contradiction with the unavoidable “opacity” (unawareness) of the brain process by which they perform their moral judgements on the right action to execute. In fact, the moral accountability of our actions depends on what is immediately before and after our “moral judgements” on the right action to execute (formally, deontic first order logic (FOL) decisions). I.e., our moral accountability depends on the “ethical constraints” we imposed to our judgement before performing it in an opaque way. Anyway, our moral accountability depends overall on the “ethical assessment” or explicit “moral reasoning” after and over the moral judgement before executing our actions (deontic higher order logic (HOL) assessment). In this way, in the light of the AI “imitation game”, the consistent attribution of the status of ethically accountable artificial moral agents to autonomous AI systems depends on two similar conditions. Firstly, it depends on the presence of “ethical constraints” to be satisfied in their Machine Learning (ML) supervised optimization algorithm during its training phase, to give the system ethical skills (“competences”) in its decisions. Secondly – and definitely—, it depends on the presence in an AI autonomous system of a deontic HOL “ethical reasoner” to perform an automatic, and fully transparent assessment (metalogical deontic valuation) about the decisions taken by the ethically skilled ML algorithm about the right action to execute, before executing it. Finally, we show that the proper deontic FOL and HOL for this class of artificial moral agents is Kripke’s modal relational logic, in its algebraic topological formalization. This is naturally implemented in the dissipative QFT unsupervised deep learning of our brains, based on the “doubling of the degrees of freedom” (DDF), and then in the so-called “deep-belief” artificial neural networks for the statistical data pre-processing. This unsupervised learning procedure is also compliant with the usage of the “maximin fairness principle”, used as a balancing aggregation principle of the statistical variables in Sen’s formal theory of fairness. (shrink)

Deep Learning has been widely used for tackling challenging natural language processing tasks over the recent years. Similarly, the application of Deep Neural Networks in legal analytics has increased significantly. In this survey, we study the early adaptation of Deep Learning in legal analytics focusing on three main fields; text classification, information extraction, and information retrieval. We focus on the semantic feature representations, a key instrument for the successful application of deep learning in (...) natural language processing. Additionally, we share pre-trained legal word embeddings using the word2vec model over large corpora, comprised legislations from UK, EU, Canada, Australia, USA, and Japan among others. (shrink)

The purpose of the study was to solve the problem of the mismatching between the supply and demand of the talents that universities provide for society, whose major is communication design. The correlations between social post demand and university cultivation, as well as between social post demand and the demand indexes of enterprises for posts, are explored under the guidance of University-Industrial Research Collaboration. The backpropagation neural network is used, and the advantages of the Seasonal Autoregressive Integrated Moving Average model (...) model are combined to design the SARIMA-BPNN model after the relevant parameters are adjusted. Through the experimental analysis, it is found that the error of the root mean square of the designed SARIMA-BP model in post prediction is 7.523 and that of the BPNN model is 16.122. The effect of the prediction model that was designed based on deep learning is smaller than that of the previous model based on the neural network, and it can predict future posts more accurately for colleges and universities. Guided by the “University-Industrial Research Collaboration,” students will have more practice in the teaching process in response to social needs. “University-Industrial Research Collaboration” guides the teaching direction for communication design majors and can help to cultivate communication design talents who are competent for the post provided. (shrink)

This paper argues that a notion of statistical explanation, based on Salmon’s statistical relevance model, can help us better understand deep neural networks. It is proved that homogeneous partitions, the core notion of Salmon’s model, are equivalent to minimal sufficient statistics, an important notion from statistical inference. This establishes a link to deep neural networks via the so-called Information Bottleneck method, an information-theoretic framework, according to which deep neural networks implicitly solve an optimization problem that generalizes minimal (...) sufficient statistics. The resulting notion of statistical explanation is general, mathematical, and subcausal. (shrink)

The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (...) (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly. (shrink)

The aim or goal of science has long been discussed by both philosophers of science and scientists themselves. In The Scientific Image (van Fraassen 1980), the aim of science is famously employed to characterize scientific realism and a version of anti-realism, called constructive empiricism. Since the publication of The Scientific Image, however, various changes have occurred in scientific practice. The increasing use of machine learning technology, especially deep learning (DL), is probably one of the major changes in (...) the last decade. This paper aims to explore the implications of DL-aided research for the aim of science debate. I argue that, while the emerging DL-aided research is unlikely to change the state of classic opposition between constructive empiricism and scientific realism, it could offer interesting cases regarding the opposition between those who espouse truth as the aim of science and those oriented to understanding (of the kind that sacrifices truth). (shrink)

Deep learning is a kind of machine learning which happens in a certain type of artificial neural networks called deep networks. Artificial deep networks, which exhibit many similarities with biological ones, have consistently shown human-like performance in many intelligent tasks. This poses the question whether this performance is caused by such similarities. After reviewing the structure and learning processes of artificial and biological neural networks, we outline two important reasons for the success of (...) class='Hi'>deep learning, namely the extraction of successively higher level features and the multiple layer structure, which are closely related to each other. Then some indications about the framing of this heated debate are given. After that, an assessment of the value of artificial deep networks as models of the human brain is given from the similarity perspective of model representation. Finally, a new version of computational functionalism is proposed which addresses the specificity of deep neural computation better than classic, program based computational functionalism. (shrink)

This exploration aims to study the emotion recognition of speech and graphic visualization of expressions of learners under the intelligent learning environment of the Internet. After comparing the performance of several neural network algorithms related to deep learning, an improved convolution neural network-Bi-directional Long Short-Term Memory algorithm is proposed, and a simulation experiment is conducted to verify the performance of this algorithm. The experimental results indicate that the Accuracy of CNN-BiLSTM algorithm reported here reaches 98.75%, which is (...) at least 3.15% higher than that of other algorithms. Besides, the Recall is at least 7.13% higher than that of other algorithms, and the recognition rate is not less than 90%. Evidently, the improved CNN-BiLSTM algorithm can achieve good recognition results, and provide significant experimental reference for research on learners’ emotion recognition and graphic visualization of expressions in an intelligent learning environment. (shrink)

Content-based image retrieval (CBIR) is a technique used to retrieve image from an image database. However, the CBIR process suffers from less accuracy to retrieve many images from an extensive image database and prove the privacy of images. The aim of this article is to address the issues of accuracy utilizing deep learning techniques such as the CNN method. Also, it provides the necessary privacy for images using fully homomorphic encryption methods by Cheon–Kim–Kim–Song (CKKS). The system has been (...) proposed, namely RCNN_CKKS, which includes two parts. The first part (offline processing) extracts automated high-level features based on a flatting layer in a convolutional neural network (CNN) and then stores these features in a new dataset. In the second part (online processing), the client sends the encrypted image to the server, which depends on the CNN model trained to extract features of the sent image. Next, the extracted features are compared with the stored features using a Hamming distance method to retrieve all similar images. Finally, the server encrypts all retrieved images and sends them to the client. Deep-learning results on plain images were 97.87% for classification and 98.94% for retriever images. At the same time, the NIST test was used to check the security of CKKS when applied to Canadian Institute for Advanced Research (CIFAR-10) dataset. Through these results, researchers conclude that deep learning is an effective method for image retrieval and that a CKKS method is appropriate for image privacy protection. (shrink)

Most e-commerce platforms allow consumers to post product reviews, causing more and more consumers to get into the habit of reading reviews before they buy. These online reviews serve as an emotional feedback of consumers’ product experience and contain a lot of important information, but inevitably there are malicious or irrelevant reviews. It is especially important to discover and identify the real sentiment tendency in online reviews in a timely manner. Therefore, a deep learning-based real online consumer sentiment (...) classification model is proposed. First, the mapping relationship between online reviews of goods and sentiment features is established based on expert knowledge and using fuzzy mathematics, thus mapping the high-dimensional original text data into a continuous low-dimensional space. Secondly, after obtaining local contextual features using convolutional operations, the long-term dependencies between features are fully considered by a bidirectional long- and short-term memory network. Then, the degree of contribution of different words to the text is considered by introducing an attention mechanism, and a regular term constraint is introduced in the objective function. The experimental results show that the proposed convolutional attention–long and short-term memory network model has a higher test accuracy of 83.3% compared with other models, indicating that the model has better classification performance. (shrink)

This paper uses an improved deep learning algorithm to judge the rationality of the design of landscape image feature recognition. The preprocessing of the image is proposed to enhance the data. The deficiencies in landscape feature extraction are further addressed based on the new model. Then, the two-stage training method of the model is used to solve the problems of long training time and convergence difficulties in deep learning. Innovative methods for zoning and segmentation training of (...) landscape pattern features are proposed, which makes model training faster and generates more creative landscape patterns. Because of the impact of too many types of landscape elements in landscape images, traditional convolutional neural networks can no longer effectively solve this problem. On this basis, a fully convolutional neural network model is designed to perform semantic segmentation of landscape elements in landscape images. Through the method of deconvolution, the pixel-level semantic segmentation is realized. Compared with the 65% accuracy rate of the convolutional neural network, the fully convolutional neural network has an accuracy rate of 90.3% for the recognition of landscape elements. The method is effective, accurate, and intelligent for the classification of landscape element design, which better improves the accuracy of classification, greatly reduces the cost of landscape element design classification, and ensures that the technical method is feasible. This paper classifies landscape behavior based on this model for full convolutional neural network landscape images and demonstrates the effectiveness of using the model. In terms of landscape image processing, the image evaluation provides a certain basis. (shrink)

We review publications in automated scientific discovery using deep learning, with the aim of shedding light on problems with strong connections to philosophy of science, of physics in particular. We show that core issues of philosophy of science, related, notably, to the nature of scientific theories; the nature of unification; and of causation loom large in scientific deep learning. Therefore, advances in deep learning could, and ideally should, have impact on philosophy of science, and (...) vice versa. We suggest lines of further research, and highlight the role ‘theory-based’ AI could have in future developments of the field. (shrink)

It has often been argued that we face a trade-off between accuracy and opacity in deep learning models. The idea is that we can only harness the accuracy of deep learning models by simultaneously accepting that the grounds for the models’ decision-making are epistemically opaque to us. In this paper, we ask the following question: what are the prospects of making deep learning models transparent without compromising on their accuracy? We argue that the answer (...) to this question depends on which kind of opacity we have in mind. If we focus on the standard notion of opacity, which tracks the internal complexities of deep learning models, we argue that existing explainable AI (XAI) techniques show us that the prospects look relatively good. But, as it has recently been argued in the literature, there is another notion of opacity that concerns factors external to the model. We argue that there are at least two types of external opacity—link opacity and structure opacity—and that existing XAI techniques can to some extent help us reduce the former but not the latter. (shrink)

Abstract : Background: Vegetable agriculture is very important to human continued existence and remains a key driver of many economies worldwide, especially in underdeveloped and developing economies. Objectives: There is an increasing demand for food and cash crops, due to the increasing in world population and the challenges enforced by climate modifications, there is an urgent need to increase plant production while reducing costs. Methods: In this paper, Lemon classification approach is presented with a dataset that contains approximately 2,000 images (...) belong to 3 species at a few developing phases. Convolutional Neural Network (CNN) algorithms, a deep learning technique extensively applied to image recognition was used, for this task. The results: found that CNN-driven lemon classification applications when used in farming automation have the latent to enhance crop harvest and improve output and productivity when designed properly. The trained model achieved an accuracy of 99.48% on a held-out test set, demonstrating the feasibility of this approach. (shrink)

In recent years, multivariate pattern analysis has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging, electroencephalography, and other neuroimaging methodologies. In a similar time frame, “deep learning” has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much (...) simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data – which we term “deep MVPA,” or dMVPA – and introduce a new software toolbox intended to facilitate dMVPA for neuroscientists everywhere. (shrink)

An original quantum foundations concept of a deep learning computational Universe is introduced. The fundamental information of the Universe (or Triuniverse)is postulated to evolve about itself in a Red, Green and Blue (RGB) tricoloured stable self-mutuality in three information processing loops. The colour is a non-optical information label. The information processing loops form a feedback-reinforced deep learning macrocycle with trefoil knot topology. Fundamental information processing is driven by ψ-Epistemic Drive, the Natural appetite for information selected for (...) advantageous knowledge. From its substrate of Mathematics, the knotted information processing loops determine emergent Physics and thence the evolution of super-emergent Life (biological and artificial intelligence). RGB-tricoloured information is processed in sequence in an Elemental feedback loop (R), then an Operational feedback loop (G), then a Structural feedback loop (B) and back to an Elemental feedback loop (R), and so on around the trefoil in deep learning macrocycles. It is postulated that hierarchical information correspondence from Mathematics through Physics to Life is mapped and conserved within each colour. The substrate of Mathematics has RGB-tricoloured feedback loops which are respectively Algebra (R), Algorithms (G) and Geometry (B). In Mathematics, the trefoil macrocycle is Algebraic Algorithmic Geometry and its correlation system is a Tensor Neural Knot Network enabling Qutrit Entanglement. Emergent Physics has corresponding RGB-tricoloured feedback loops of Quantum Mechanics (R), Quantum Deep Learning (G) and Quantum Geometrodynamics(B). In Physics, the trefoil macrocycle is Quantum Intelligent Geometrodynamics and its correlation system is Quantum Darwinism. Super-emergent Life has corresponding RGB-tricoloured loops of Variation (R), Selection (G) and Heredity (B). In the evolution of Life, the trefoil macrocycle is Variational Selective Heredity and its correlation ecosystem is Darwin’s ecologically “Entangled Bank”. (shrink)

The novel coronavirus disease is regarded as one of the most imminent disease outbreaks which threaten public health on various levels worldwide. Because of the unpredictable outbreak nature and the virus’s pandemic intensity, people are experiencing depression, anxiety, and other strain reactions. The response to prevent and control the new coronavirus pneumonia has reached a crucial point. Therefore, it is essential—for safety and prevention purposes—to promptly predict and forecast the virus outbreak in the course of this troublesome time to have (...) control over its mortality. Recently, deep learning models are playing essential roles in handling time-series data in different applications. This paper presents a comparative study of two deep learning methods to forecast the confirmed cases and death cases of COVID-19. Long short-term memory and gated recurrent unit have been applied on time-series data in three countries: Egypt, Saudi Arabia, and Kuwait, from 1/5/2020 to 6/12/2020. The results show that LSTM has achieved the best performance in confirmed cases in the three countries, and GRU has achieved the best performance in death cases in Egypt and Kuwait. (shrink)

This study aimed to develop cross-domain deep learning courses of artificial intelligence in vocational senior high schools and explore its impact on students’ learning effects. It initially adopted a literature review to develop a cross-domain SPOC-AIoT Course with SPOC and the Double Diamond 4D model in vocational senior high schools. Afterward, it adopted participatory action research and a questionnaire survey and conducted analyses on the various aspects of the technology acceptance model by SmartPLS. Further, this study explored (...) the impact on the effects of deep learning and knowledge-ability learning of artificial intelligence after 16 weeks of course teaching among 36 Grade I students from the electrical and electronic group of a vocational senior high school. This study revealed that the four stages of the SPOC-AIoT Teaching Mode of the Double Diamond 4D model may effectively guide students to learn AIoT knowledge and skills. Based on the technology acceptance model, the analysis of learning and participation in SmartPLS indicated that this model conformed to the academic fitness requirements of the overall model. After learning with the SPOC-AIoT Teaching Mode, the learning effects of students in AIoT have been significantly improved to a positive aspect. Finally, some suggestions were put forward to promote the development of the SPOC-AIoT Teaching Mode Course in the future. (shrink)

Brain–computer interfaces (BCIs) utilizing machine learning techniques are an emerging technology that enables a communication pathway between a user and an external system, such as a computer. Owing to its practicality, electroencephalography (EEG) is one of the most widely used measurements for BCI. However, EEG has complex patterns and EEG-based BCIs mostly involve a cost/time-consuming calibration phase; thus, acquiring sufficient EEG data is rarely possible. Recently, deep learning (DL) has had a theoretical/practical impact on BCI research because (...) of its use in learning representations of complex patterns inherent in EEG. Moreover, algorithmic advances in DL facilitate short/zero-calibration in BCI, thereby suppressing the data acquisition phase. Those advancements include data augmentation (DA), increasing the number of training samples without acquiring additional data, and transfer learning (TL), taking advantage of representative knowledge obtained from one dataset to address the so-called data insufficiency problem in other datasets. In this study, we review DL-based short/zero-calibration methods for BCI. Further, we elaborate methodological/algorithmic trends, highlight intriguing approaches in the literature, and discuss directions for further research. In particular, we search forgenerative model-based andgeometric manipulation-based DA methods. Additionally, we categorize TL techniques in DL-based BCIs intoexplicitandimplicitmethods. Our systematization reveals advances in the DA and TL methods. Among the studies reviewed herein, ~45% of DA studies used generative model-based techniques, whereas ~45% of TL studies used explicit knowledge transferring strategy. Moreover, based on our literature review, we recommend an appropriate DA strategy for DL-based BCIs and discuss trends of TLs used in DL-based BCIs. (shrink)

In recent years, deep learning as the requirement of higher education for students has attracted the attention of many scholars, and previous studies focused on defining deep learning as the deep processing of knowledge of the brain, however, in the process of knowledge processing, the brain not only involves the deep processing of information but also participates in learning consciously and emotionally. Therefore, this research proposed a four-factor model hypothesis for deep (...) class='Hi'>learning that includes deep learning investment, deep cognitive-emotional experience, deep information processing, and deep learning meta-cognitive. In addition, the research proposed teachers’ emotional support perceived by students has an effect on the four factors of deep learning. Through SPSS 26 and AMOS 24, this research has verified the four-factor model of deep learning applying exploratory factor analysis and confirmatory factor analysis and verified that the perceived teacher emotional support has an impact on the four factors of students’ deep learning using the SEM. (shrink)

Abstract: Potatoes are edible tubers, available worldwide and all year long. They are relatively cheap to grow, rich in nutrients, and they can make a delicious treat. The humble potato has fallen in popularity in recent years, due to the interest in low-carb foods. However, the fiber, vitamins, minerals, and phytochemicals it provides can help ward off disease and benefit human health. They are an important staple food in many countries around the world. There are an estimated 200 varieties of (...) potatoes, which can be classified into a number of categories based on the cooked texture and ingredient functionality. Using a public dataset of 2400 images of potatoes, we trained a deep convolutional neural network to identify 4 types (Red, Red Washed, Sweet, and White).The trained model achieved an accuracy of 99.5% of test set, demonstrating the feasibility of this approach. (shrink)

Eye-tracking technology has become a powerful tool for biomedical-related applications due to its simplicity of operation and low requirements on patient language skills. This study aims to use the machine-learning models and deep-learning networks to identify key features of eye movements in Alzheimer's Disease (AD) under specific visual tasks, thereby facilitating computer-aided diagnosis of AD. Firstly, a three-dimensional (3D) visuospatial memory task is designed to provide participants with visual stimuli while their eye-movement data are recorded and used (...) to build an eye-tracking dataset. Then, we propose a novel deep-learning-based model for identifying patients with Alzheimer's Disease (PwAD) and healthy controls (HCs) based on the collected eye-movement data. The proposed model utilizes a nested autoencoder network to extract the eye-movement features from the generated fixation heatmaps and a weight adaptive network layer for the feature fusion, which can preserve as much useful information as possible for the final binary classification. To fully verify the performance of the proposed model, we also design two types of models based on traditional machine-learning and typical deep-learning for comparison. Furthermore, we have also done ablation experiments to verify the effectiveness of each module of the proposed network. Finally, these models are evaluated by four-fold cross-validation on the built eye-tracking dataset. The proposed model shows 85% average accuracy in AD recognition, outperforming machine-learning methods and other typical deep-learning networks. (shrink)

The use of ensemble learning, deep learning, and effective document representation methods is currently some of the most common trends to improve the overall accuracy of a text classification/categorization system. Ensemble learning is an approach to raise the overall accuracy of a classification system by utilizing multiple classifiers. Deep learning-based methods provide better results in many applications when compared with the other conventional machine learning algorithms. Word embeddings enable representation of words learned from (...) a corpus as vectors that provide a mapping of words with similar meaning to have similar representation. In this study, we use different document representations with the benefit of word embeddings and an ensemble of base classifiers for text classification. The ensemble of base classifiers includes traditional machine learning algorithms such as naïve Bayes, support vector machine, and random forest and a deep learning-based conventional network classifier. We analysed the classification accuracy of different document representations by employing an ensemble of classifiers on eight different datasets. Experimental results demonstrate that the usage of heterogeneous ensembles together with deep learning methods and word embeddings enhances the classification performance of texts. (shrink)

This work aims to explore the application of deep learning-based artificial intelligence technology in sentencing, to promote the reform and innovation of the judicial system. First, the concept and the principles of sentencing are introduced, and the deep learning model of intelligent robot in trials is proposed. According to related concepts, the issues that need to be solved in artificial intelligence sentencing based on deep learning are introduced. The deep learning model is (...) integrated into the intelligent robot system, to assist in the sentencing of cases. Finally, an example is adopted to illustrate the feasibility of the intelligent robot under deep learning in legal sentencing. The results show that the general final trial periods for cases of traffic accidents, copyright information, trademark infringement, copyright protection, and theft are 1,049, 796, 663, 847, and 201 days, respectively; while the final trial period under artificial intelligence evaluation based on the restricted Boltzmann deep learning model is 458, 387, 376, 438, and 247 days, respectively. The accuracy of trials is above 92%, showing a high application value. It can be observed that expect theft cases, the final trial period for others cases has been effectively reduced. The intelligent robot assistance under the restricted Boltzmann deep learning model can shorten the trial period of cases. The deep learning intelligent robot has a certain auxiliary role in legal sentencing, and this outcome provides a theoretical basis for the research of artificial intelligence technology in legal sentencing. (shrink)

Repetitive practice is one of the most important factors in improving the performance of motor skills. This paper focuses on the analysis and classification of forearm gestures in the context of violin playing. We recorded five experts and three students performing eight traditional classical violin bow-strokes: martelé, staccato, detaché, ricochet, legato, trémolo, collé, and col legno. To record inertial motion information, we utilized the Myo sensor, which reports a multidimensional time-series signal. We synchronized inertial motion recordings with audio data to (...) extract the spatiotemporal dynamics of each gesture. Applying state-of-the-art deep neural networks, we implemented and compared different architectures where convolutional neural networks models demonstrated recognition rates of 97.147%, 3DMultiHeaded_CNN models showed rates of 98.553%, and rates of 99.234% were demonstrated by CNN_LSTM models. The collected data contained sufficient information to distinguish the bowing techniques studied, and deep learning methods were capable of learning the movement patterns that distinguish these techniques. Each of the learning algorithms investigated produced high classification accuracies which supported the feasibility of training classifiers. The resulting classifiers may provide the foundation of a digital assistant to enhance musicians' time spent practicing alone, providing real-time feedback on the accuracy and consistency of their musical gestures in performance. (shrink)