Problem Domain Research Articles

On the computational complexity of ethics: moral tractability for minds and machines

Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of ethical problems based on consequentialism, deontology, and virtue ethics, with the aim of elucidating the complexity associated with the problems themselves (e.g., due to combinatorics, uncertainty, strategic dynamics), the computational methods employed (e.g., probability, logic, learning), and the available resources (e.g., time, knowledge, learning). The results indicate that most problems the normative frameworks pose lead to tractability issues in every category analyzed. Our investigation also provides several insights about the computational nature of normative ethics, including the differences between rule- and outcome-based moral strategies, and the implementation-variance with regard to moral resources. We then discuss the consequences complexity results have for the prospect of moral machines in virtue of the trade-off between optimality and efficiency. Finally, we elucidate how computational complexity can be used to inform both philosophical and cognitive-psychological research on human morality by advancing the moral tractability thesis.

A boundary value problem for the fourth-order degenerate equation of the mixed type

Many problems in mechanics, physics, and geophysics lead to solving partial differential equations that are not included in the known classes of elliptic, parabolic or hyperbolic equations. Such equations, as a rule, began to be called non-classical equations of mathematical physics. The theory of degenerate equations is one of the central branches of the modern theory of partial differential equations. This is primarily due to the identification of a variety of applied problems, the mathematical modeling of which serves the study of various types of degenerate equations. The study of boundary value problems for mixed type’s equations of the fourth-order with power-law degeneration remains relevant. In this work, a boundary value problem in a rectangular domain for a degenerate equation of the fourth-order mixed-type is posed and investigated. Well-posedness of the boundary value problem for a fourth-order partial differential equation is established by proving the existence and uniqueness of the solution. Under sufficient conditions, a solution to the problem under consideration was explicitly found by the variable separation method.

Comparing Hierarchical Approaches to Enhance Supervised Emotive Text Classification

The performance of emotive text classification using affective hierarchical schemes (e.g., WordNet-Affect) is often evaluated using the same traditional measures used to evaluate the performance of when a finite set of isolated classes are used. However, applying such measures means the full characteristics and structure of the emotive hierarchical scheme are not considered. Thus, the overall performance of emotive text classification using emotion hierarchical schemes is often inaccurately reported and may lead to ineffective information retrieval and decision making. This paper provides a comparative investigation into how methods used in hierarchical classification problems in other domains, which extend traditional evaluation metrics to consider the characteristics of the hierarchical classification scheme, can be applied and subsequently improve the classification of emotive texts. This study investigates the classification performance of three widely used classifiers, Naive Bayes, J48 Decision Tree, and SVM, following the application of the aforementioned methods. The results demonstrated that all the methods improved the emotion classification. However, the most notable improvement was recorded when a depth-based method was applied to both the testing and validation data, where the precision, recall, and F1-score were significantly improved by around 70 percentage points for each classifier.

The first boundary value problem for the fractional diffusion equation in a degenerate angular domain

This article addresses the problems observed in branching fractal structures, where super-slow transport processes can occur, a phenomenon described by diffusion equations with a fractional time derivative. The characteristic feature of these processes is their extremely slow relaxation rate, where a physical quantity changes more gradually than its first derivative. Such phenomena are sometimes categorized as processes with “residual memory”. The study presents a solution to the first boundary problem in an angular domain degenerating into a point at the initial moment of time for a fractional diffusion equation with the RiemannLiouville fractional differentiation operator with respect to time. It establishes the existence theorem of the problem under investigation and constructs a solution representation. The need for understanding these super-slow processes and their impact on fractal structures is identified and justified. The paper demonstrates how these processes contribute to the broader understanding of fractional diffusion equations, proving the theorem’s existence and formulating a solution representation.

Route Planning Algorithms for Fleets of Connected Vehicles: State of the Art, Implementation, and Deployment

The introduction of 5G technologies has enabled the possibility of designing and building several new classes of networked information systems that were previously impossible to implement due to limitations on data throughput or the reliability of transmission channels. Among them, one of the most interesting and successful examples with a highly positive impact in terms of the quality of urban environments and societal and economical welfare is a system of semi-autonomous connected vehicles, where IoT devices, data centers, and fleets of smart vehicles equipped with communication and computational resources are combined into a heterogeneous and distributed infrastructure, unifying hardware, networks, and software. In order to efficiently provide various services (e.g., patrolling, pickup and delivery, monitoring), these systems typically rely on collecting and broadcasting large amounts of data (e.g., sensor data, GPS traces, or maps), which need to be properly collected and processed in a timely manner. As is well documented in the literature, one of the most effective ways to achieve this purpose, especially in a real-time context, is to adopt a graph model of the data (e.g., to model communication networks, roads, or interactions between vehicles) and to employ suitable graph algorithms to solve properly defined computational problems of interest (e.g., shortest paths or distributed consensus). While research in this context has been extensive from a theoretical perspective, works that have focused on the implementation, deployment, and evaluation of the practical performance of graph algorithms for real-world systems of autonomous vehicles have been much rarer. In this paper, we present a study of this kind. Specifically, we first describe the main features of a real-world information system employing semi-autonomous connected vehicles that is currently being tested in the city of L’Aquila (Italy). Then, we present an overview of the computational challenges arising in the considered application domain and provide a systematic survey of known algorithmic results for one of the most relevant classes of computational problems that have to be addressed in said domain, namely, pickup and delivery problems. Finally, we discuss implementation issues, adopted software tools, and the deployment and testing phases concerning one of the algorithmic components of the mentioned real-world system dedicated to handling a specific problem of the above class, namely, the pickup and delivery multi-vehicle problem with time windows.

Multiphysics Missing Data Synthesis: A Machine Learning Approach for Mitigating Data Gaps and Artifacts

Abstract The presence of gaps and spurious nonphysical artifacts in datasets is a nearly ubiquitous problem in many scientific and engineering domains. In the context of multiphysics numerical models, data gaps may arise from lack of coordination between modeling elements and limitations of the discretization and solver schemes employed. In the case of data derived from physical experiments, the limitations of sensing and data acquisition technologies, as well as myriad sources of experimental noise, may result in the generation of data gaps and artifacts. In the present work, we develop and demonstrate a machine learning (ML) meta-framework for repairing such gaps in multiphysics datasets. A unique “cross-training” methodology is used to ensure that the ML models capture the underlying multiphysics of the input datasets, without requiring training on datasets free of gaps/artifacts. The general utility of this approach is demonstrated by the repair of gaps in a multiphysics dataset taken from hypervelocity impact simulations. Subsequently, we examine the problem of removing scan artifacts from X-ray computed microtomographic (XCMT) datasets. A unique experimental methodology for acquiring XCMT data, wherein articles are scanned multiple times under different conditions, enables the ready identification of artifacts, their removal from the datasets, and the filling of the resulting gaps using the ML framework. This work concludes with observations regarding the unique features of the developed methodology, and a discussion of potential future developments and applications for this technology.

Gender classification based on gait analysis using ultrawide band radar augmented with artificial intelligence

The identification of individuals based on their walking patterns, also known as gait recognition, has garnered considerable interest as a biometric trait. The use of gait patterns for gender classification has emerged as a significant research domain with diverse applications across multiple fields. The present investigation centers on the classification of gender based on gait utilizing data from Ultra-wide band radar. A total of 181 participants were included in the study, and data was gathered using Ultra-wide band radar technology. This study investigates various preprocessing techniques, feature extraction methods, and dimensionality reduction approaches to efficiently process Ultra-wide band radar data. The data quality is improved through the utilization of a two-pulse canceller and discrete wavelet transform. The hybrid feature dataset is generated through the creation of gray-level co-occurrence matrices and subsequent extraction of statistical features. Principal Component Analysis is utilized for dimensionality reduction, and prediction probabilities are incorporated as features for classification optimization. The present study employs k-fold cross-validation to train and assess machine learning classifiers, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, Multi-Layer Perceptron, K-Nearest Neighbors, and Extra Tree Classifier. The Multilayer Perceptron exhibits superior performance, achieving an accuracy of 0.936. The Support Vector Machine and k-Nearest Neighbors classifiers closely trail behind, both achieving an accuracy of 0.934. This research is of the utmost importance due to its capacity to offer solutions to crucial problems in multiple domains. The findings indicate that the utilization of UWB radar data for gait-based gender classification holds promise in diverse domains, including biometrics, surveillance, and healthcare. The present study makes a valuable contribution to the progress of gender classification systems that rely on gait patterns.

Analysis of Moving Bodies with a Direct Finite Difference Time Domain Method

This paper proposes an original and thorough analysis of the behavior of electromagnetic waves in the presence of moving bodies by using the finite difference time domain (FDTD) method. Movements are implemented by changing positions of the objects at each time step, through the classical FDTD time loop. This technique is suitable for non-relativistic speeds, thus for most encountered problems in antennas and propagation domain. The numerical aspects that need to be considered are studied. Then, different bodies in motion are examined: plane wave source with matching resistors, observation point, inclined partially reflecting surface (PRS), line source, and metallic cylinder illuminated by a plane wave. The results are compared with those of special relativity which are considered as the references. Some aspects of special relativity are present in the direct FDTD approach, such as the independence of the velocity of electromagnetic wave propagation with the speed of the source and Lorentz local time (with a different physical interpretation). It is shown that the amplitude of the electric field for a moving plane wave source does not increase with the speed of motion, if the impedance of the source is small. Moreover, for a moving scattering metallic wire, one can observe a phenomenon similar to shock waves.

Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint)

Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems because people easily understand them, they apply across different problem domains and seem to be legally compliant. Although over 100 counterfactual methods exist in the XAI literature, each claiming to generate plausible explanations akin to those preferred by people, few of these methods have actually been tested on users (∼7%). Even fewer studies adopt a user-centered perspective; for instance, asking people for their counterfactual explanations to determine their perspective on a “good explanation”. This gap in the literature is addressed here using a novel methodology that (i) gathers human-generated counterfactual explanations for misclassified images, in two user studies and, then, (ii) compares these human-generated explanations to computationally-generated explanations for the same misclassifications. Results indicate that humans do not “minimally edit” images when generating counterfactual explanations. Instead, they make larger, “meaningful” edits that better approximate prototypes in the counterfactual class. An analysis based on “explanation goals” is proposed to account for this divergence between human and machine explanations. The implications of these proposals for future work are discussed.

Using Symmetries to Lift Satisfiability Checking

We analyze how symmetries can be used to compress structures (also known as interpretations) onto a smaller domain without loss of information. This analysis suggests the possibility to solve satisfiability problems in the compressed domain for better performance. Thus, we propose a 2-step novel method: (i) the sentence to be satisfied is automatically translated into an equisatisfiable sentence over a ``lifted'' vocabulary that allows domain compression; (ii) satisfiability of the lifted sentence is checked by growing the (initially unknown) compressed domain until a satisfying structure is found. The key issue is to ensure that this satisfying structure can always be expanded into an uncompressed structure that satisfies the original sentence to be satisfied. We present an adequate translation for sentences in typed first-order logic extended with aggregates. Our experimental evaluation shows large speedups for generative configuration problems. The method also has applications in the verification of software operating on complex data structures. Our results justify further research in automatic translation of sentences for symmetry reduction.

Offline Model-Based Optimization via Policy-Guided Gradient Search

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has to optimize an unknown function given only its offline evaluation at a fixed set of inputs. A naive solution to this problem is to learn a surrogate model of the unknown function and optimize this surrogate instead. However, such a naive optimizer is prone to erroneous overestimation of the surrogate (possibly due to over-fitting on a biased sample of function evaluation) on inputs outside the offline dataset. Prior approaches addressing this challenge have primarily focused on learning robust surrogate models. However, their search strategies are derived from the surrogate model rather than the actual offline data. To fill this important gap, we introduce a new learning-to-search perspective for offline optimization by reformulating it as an offline reinforcement learning problem. Our proposed policy-guided gradient search approach explicitly learns the best policy for a given surrogate model created from the offline data. Our empirical results on multiple benchmarks demonstrate that the learned optimization policy can be combined with existing offline surrogates to significantly improve the optimization performance.

Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation

Understanding and accurately explaining compatibility relationships between fashion items is a challenging problem in the burgeoning domain of AI-driven outfit recommendations. Present models, while making strides in this area, still occasionally fall short, offering explanations that can be elementary and repetitive. This work aims to address these shortcomings by introducing the Pair Fashion Explanation (PFE) dataset, a unique resource that has been curated to illuminate these compatibility relationships. Furthermore, we propose an innovative two stage pipeline model that leverages this dataset. This fine-tuning allows the model to generate explanations that convey the compatibility relationships between items. Our experiments showcase the model's potential in crafting descriptions that are knowledgeable, aligned with ground-truth matching correlations, and that produce understandable and informative descriptions, as assessed by both automatic metrics and human evaluation. Our code and data are released at https://github.com/wangyu-ustc/PairFashionExplanation.

Conversational Modeling for Constraint Satisfaction

Many problems, from Sudoku to factory scheduling, can be regarded as constraint satisfaction problems. A key component of real world problem solving is a conversation between a constraint programming expert and a problem domain expert to specify the problem to be solved. This presentation argues that the time is ripe for progress in automating the constraint programmer side of this conversation and suggests promising avenues for this pursuit.

Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems

The Alternating Direction Method of Multipliers (ADMM) has gained significant attention across a broad spectrum of machine learning applications. Incorporating the over-relaxation technique shows potential for enhancing the convergence rate of ADMM. However, determining optimal algorithmic parameters, including both the associated penalty and relaxation parameters, often relies on empirical approaches tailored to specific problem domains and contextual scenarios. Incorrect parameter selection can significantly hinder ADMM's convergence rate. To address this challenge, in this paper we first propose a general approach to optimize the value of penalty parameter, followed by a novel closed-form formula to compute the optimal relaxation parameter in the context of linear quadratic problems (LQPs). We then experimentally validate our parameter selection methods through random instantiations and diverse imaging applications, encompassing diffeomorphic image registration, image deblurring, and MRI reconstruction.

A symmetry result for fully nonlinear problems in exterior domains

We study an overdetermined fully nonlinear problem driven by one of the Pucci’s Extremal Operators in an external domain. Under certain decay assumptions on the solution, we extend Serrin’s symmetry result, i.e, every domain where the solution exists must be radial.

Performance Analysis and Evaluation of Clustering Algorithms using WEKA

Clustering, an unsupervised learning technique, to find inherent groupings in un-labelled data. It seems to be referring to a study or research paper that examines and uses a number of clustering algorithms, including the canopy method, k-Means clustering, hierarchical clustering, density-based clustering, and EM algorithm. WEKA, a clustering program, is used for the examination of these techniques. and the effectiveness of these algorithms is evaluated through experiments using social network Ads datasets. The goal of this research paper or study seems to be to assess how well these clustering algorithms perform in grouping data within social network Ads datasets. Such analyses can help identify the most suitable algorithm for a specific type of data or problem domain and may lead to insights into the underlying structure of the data.

Transfer learning for metamaterial design and simulation

Abstract We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface arrays under open boundary conditions in electromagnetic metamaterials. Our aim is to assess the efficiency of transfer learning across a range of problem domains that vary in their resemblance to the original base problem for which the ResNet model was initially trained. We use a quasi-analytical discrete dipole approximation (DDA) method to simulate electrically large metasurface arrays to obtain ground truth data for training and testing of our deep neural network. Our approach can save significant time for examining novel metasurface designs by harnessing the power of transfer learning, as it effectively mitigates the pervasive data bottleneck issue commonly encountered in deep learning. We demonstrate that for the best case when the transfer task is sufficiently similar to the target task, a new task can be effectively trained using only a few data points yet still achieve a test mean absolute relative error of 3 % with a pre-trained neural network, realizing data reduction by a factor of 1000.

Stochastic neuro-fuzzy system implemented in memristor crossbar arrays.

Neuro-symbolic artificial intelligence has garnered considerable attention amid increasing industry demands for high-performance neural networks that are interpretable and adaptable to previously unknown problem domains with minimal reconfiguration. However, implementing neuro-symbolic hardware is challenging due to the complexity in symbolic knowledge representation and calculation. We experimentally demonstrated a memristor-based neuro-fuzzy hardware based on TiN/TaOx/HfOx/TiN chips that is superior to its silicon-based counterpart in terms of throughput and energy efficiency by using array topological structure for knowledge representation and physical laws for computing. Intrinsic memristor variability is fully exploited to increase robustness in knowledge representation. A hybrid in situ training strategy is proposed for error minimizing in training. The hardware adapts easier to a previously unknown environment, achieving ~6.6 times faster convergence and ~6 times lower error than deep learning. The hardware energy efficiency is over two orders of magnitude greater than field-programmable gate arrays. This research greatly extends the capability of memristor-based neuromorphic computing systems in artificial intelligence.

Study of convergence speed of chaotic particle swarm optimization algorithm

AbstractThis study introduces the Chaotic Particle Swarm Optimization as an innovative variant of the traditional particle swarm optimization algorithm, addressing the issue of particle swarm optimization getting trapped in local minima with a low convergence characteristic during later iterations. Chaotic particle swarm optimization incorporates principles from chaos theory to enhance the swarm's exploration and exploitation capabilities. By introducing controlled chaotic behavior, particles exhibit more diverse and unpredictable movements in the search space, leading to improved global convergence and escape from local minima. The proposed method has been implemented and evaluated on benchmark problems to assess its effectiveness. The integration of chaos theory with particle swarm optimization offers promising opportunities for developing robust and efficient optimization techniques suitable for complex and dynamic problem domains in various real-world applications.

Adaptive habitat biogeography-based optimizer for optimizing deep CNN hyperparameters in image classification

Deep Convolutional Neural Networks (DCNNs) have shown remarkable success in image classification tasks, but optimizing their hyperparameters can be challenging due to their complex structure. This paper develops the Adaptive Habitat Biogeography-Based Optimizer (AHBBO) for tuning the hyperparameters of DCNNs in image classification tasks. In complicated optimization problems, the BBO suffers from premature convergence and insufficient exploration. In this regard, an adaptable habitat is presented as a solution to these problems; it would permit variable habitat sizes and regulated mutation. Better optimization performance and a greater chance of finding high-quality solutions across a wide range of problem domains are the results of this modification's increased exploration and population diversity. AHBBO is tested on 53 benchmark optimization functions and demonstrates its effectiveness in improving initial stochastic solutions and converging faster to the optimum. Furthermore, DCNN-AHBBO is compared to 23 well-known image classifiers on nine challenging image classification problems and shows superior performance in reducing the error rate by up to 5.14%. Our proposed algorithm outperforms 13 benchmark classifiers in 87 out of 95 evaluations, providing a high-performance and reliable solution for optimizing DNNs in image classification tasks. This research contributes to the field of deep learning by proposing a new optimization algorithm that can improve the efficiency of deep neural networks in image classification.