Search

Accurate short-term prediction of phase-resolved water wave conditions is crucial for decision-making in ocean engineering. However, the initialization of remote-sensing-based wave prediction models first requires a reconstruction of wave surfaces from sparse measurements like radar. Existing reconstruction methods either rely on computationally intensive optimization procedures or simplistic modeling assumptions that compromise real-time capability or accuracy of the entire prediction process. We therefore address these issues by proposing a novel approach for phase-resolved wave surface reconstruction using neural networks based on the U-Net and Fourier neural operator (FNO) architectures. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids, that is generated by the high-order spectral method for wave simulation and a geometric radar modeling approach. The investigation reveals that both models deliver accurate wave reconstruction results and show good generalization for different sea states when trained with spatio-temporal radar data containing multiple historic radar snapshots in each input. Notably, the FNO-based network performs better in handling the data structure imposed by wave physics due to its global approach to learn the mapping between input and desired output in Fourier space., 19 pages, 13 figures (without appendix), preprint

Traffic forecasting problem remains a challenging task in the intelligent transportation system due to its spatio-temporal complexity. Although temporal dependency has been well studied and discussed, spatial dependency is relatively less explored due to its large variations, especially in the urban environment. In this study, a novel graph convolutional network model, Multi-Weight Traffic Graph Convolutional (MW-TGC) network, is proposed and applied to two urban networks with contrasting geometric constraints. The model conducts graph convolution operations on speed data with multi-weighted adjacency matrices to combine the features, including speed limit, distance, and angle. The spatially isolated dimension reduction operation is conducted on the combined features to learn the dependencies among the features and reduce the size of the output to a computationally feasible level. The output of multi-weight graph convolution is applied to the sequence-to-sequence model with Long Short-Term Memory units to learn temporal dependencies. When applied to two urban sites, urban-core and urban-mix, MW-TGC network not only outperformed the comparative models in both sites but also reduced variance in the heterogeneous urban-mix network. We conclude that MW-TGC network can provide a robust traffic forecasting performance across the variations in spatial complexity, which can be a strong advantage in urban traffic forecasting., Comment: 11 pages, 7 figures, Accepted to IEEE Transactions on Intelligent Transportation Systems (2020)

The field of steganography has experienced a surge of interest due to the recent advancements in AI-powered techniques, particularly in the context of multimodal setups that enable the concealment of signals within signals of a different nature. The primary objectives of all steganographic methods are to achieve perceptual transparency, robustness, and large embedding capacity - which often present conflicting goals that classical methods have struggled to reconcile. This paper extends and enhances an existing image-in-audio deep steganography method by focusing on improving its robustness. The proposed enhancements include modifications to the loss function, utilization of the Short-Time Fourier Transform (STFT), introduction of redundancy in the encoding process for error correction, and buffering of additional information in the pixel subconvolution operation. The results demonstrate that our approach outperforms the existing method in terms of robustness and perceptual transparency., 8 pages, 5 figures, 2 tables

In many developing nations, a lack of poverty data prevents critical humanitarian organizations from responding to large-scale crises. Currently, socioeconomic surveys are the only method implemented on a large scale for organizations and researchers to measure and track poverty. However, the inability to collect survey data efficiently and inexpensively leads to significant temporal gaps in poverty data; these gaps severely limit the ability of organizational entities to address poverty at its root cause. We propose a transfer learning model based on surface temperature change and remote sensing data to extract features useful for predicting poverty rates. Machine learning, supported by data sources of poverty indicators, has the potential to estimate poverty rates accurately and within strict time constraints. Higher temperatures, as a result of climate change, have caused numerous agricultural obstacles, socioeconomic issues, and environmental disruptions, trapping families in developing countries in cycles of poverty. To find patterns of poverty relating to temperature that have the highest influence on spatial poverty rates, we use remote sensing data. The two-step transfer model predicts the temperature delta from high resolution satellite imagery and then extracts image features useful for predicting poverty. The resulting model achieved 80% accuracy on temperature prediction. This method takes advantage of abundant satellite and temperature data to measure poverty in a manner comparable to the existing survey methods and exceeds similar models of poverty prediction., 12 pages, 3 figures, title page included

Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby obtaining the same or similar results as the original scientists. It is an essential ingredient of the scientific method and crucial for gaining trust in relevant claims. A reproducibility crisis has been recently acknowledged by scientists and this seems to affect even more Artificial Intelligence and Machine Learning, due to the complexity of the models at the core of their recent successes. Notwithstanding the recent debate on Artificial Intelligence reproducibility, its practical implementation is still insufficient, also because many technical issues are overlooked. In this survey, we critically review the current literature on the topic and highlight the open issues. Our contribution is three-fold. We propose a concise terminological review of the terms coming into play. We collect and systematize existing recommendations for achieving reproducibility, putting forth the means to comply with them. We identify key elements often overlooked in modern Machine Learning and provide novel recommendations for them. We further specialize these for two critical application domains, namely the biomedical and physical artificial intelligence fields.

The mapping and analysis of scientific knowledge makes it possible to identify the dynamics and/or growth of a particular field of research or to support strategic decisions related to different research entities, based on bibliometric and/or scientometric indicators. However, with the exponential growth of scientific production, a systematic and data-oriented approach to the analysis of this large set of productions becomes increasingly essential. Thus, in this work, a data-oriented methodology was proposed, combining Data Analysis, Machine Learning and Complex Network Analysis techniques, and Data Version Control (DVC) tool, for the extraction of implicit knowledge in scientific production bases. In addition, the approach was validated through a case study in a COVID-19 manuscripts dataset, which had 199,895 articles published on arXiv, bioRxiv, medRxiv, PubMed and Scopus databases. The results suggest the feasibility of the proposed methodology, indicating the most active countries and the most explored themes in each period of the pandemic. Therefore, this study has the potential to instrument and expand strategic decisions by the scientific community, aiming at extracting knowledge that supports the fight against the COVID-19 pandemic.

The VSTOXX index tracks the expected 30-day volatility of the EURO STOXX 50 equity index. Futures on the VSTOXX index can, therefore, be used to hedge against economic uncertainty. We investigate the effect of trader inventory on the price of VSTOXX futures through a combination of stochastic processes and machine learning methods. We formulate a simple and efficient pricing methodology for VSTOXX futures, which assumes a Heston-type stochastic process for the underlying EURO STOXX 50 market. Under these dynamics, approximate analytical formulas for the implied volatility smile and the VSTOXX index have recently been derived. We use the EURO STOXX 50 option implied volatilities and the VSTOXX index value to estimate the parameters of this Heston model. Following the calibration, we calculate theoretical VSTOXX futures prices and compare them to the actual market prices. While theoretical and market prices are usually in line, we also observe time periods, during which the market price does not agree with our Heston model. We collect a variety of market features that could potentially explain the price deviations and calibrate two machine learning models to the price difference: a regularized linear model and a random forest. We find that both models indicate a strong influence of accumulated trader positions on the VSTOXX futures price.

We demonstrate that if consciousness is relevant for the temporal evolution of a system's states -- that is, if it is dynamically relevant -- then AI systems cannot be conscious. That is because AI systems run on CPUs, GPUs, TPUs or other processors which have been designed and verified to adhere to computational dynamics that systematically preclude or suppress deviations. The design and verification preclude or suppress, in particular, potential consciousness-related dynamical effects, so that if consciousness is dynamically relevant, AI systems cannot be conscious.

Conventional recommender systems are required to train the recommendation model using a centralized database. However, due to data privacy concerns, this is often impractical when multi-parties are involved in recommender system training. Federated learning appears as an excellent solution to the data isolation and privacy problem. Recently, Graph neural network (GNN) is becoming a promising approach for federated recommender systems. However, a key challenge is to conduct embedding propagation while preserving the privacy of the graph structure. Few studies have been conducted on the federated GNN-based recommender system. Our study proposes the first vertical federated GNN-based recommender system, called VerFedGNN. We design a framework to transmit: (i) the summation of neighbor embeddings using random projection, and (ii) gradients of public parameter perturbed by ternary quantization mechanism. Empirical studies show that VerFedGNN has competitive prediction accuracy with existing privacy preserving GNN frameworks while enhanced privacy protection for users' interaction information., Comment: 17 pages, 9 figures

Algorithmic fairness is of utmost societal importance, yet the current trend in large-scale machine learning models requires training with massive datasets that are typically biased. In this context, pre-processing methods that focus on modeling and correcting bias in the data emerge as valuable approaches. In this paper, we propose FairShap, a novel pre-processing (re-weighting) method for fair algorithmic decision-making through data valuation by means of Shapley Values. Our approach is model agnostic and easily interpretable, as it measures the contribution of each training data point to a predefined fairness metric. We empirically validate FairShap on several state-of-the-art datasets of different nature, with a variety of training scenarios and models and show how it outperforms other methods, yielding fairer models with higher or similar levels of accuracy. We also illustrate FairShap's interpretability by means of histograms and latent space visualizations. We believe that this work represents a promising direction in interpretable and model-agnostic approaches to algorithmic fairness that yield competitive accuracy even when only biased datasets are available., Comment: 12 pages, 6 figures, 1 appendix

Civilizations have tried to make drinking water safe to consume for thousands of years. The process of determining water contaminants has evolved with the complexity of the contaminants due to pesticides and heavy metals. The routine procedure to determine water safety is to use targeted analysis which searches for specific substances from some known list; however, we do not explicitly know which substances should be on this list. Before experimentally determining which substances are contaminants, how do we answer the sampling problem of identifying all the substances in the water? Here, we present an approach that builds on the work of Jaanus Liigand et al., which used non-targeted analysis that conducts a broader search on the sample to develop a random-forest regression model, to predict the names of all the substances in a sample, as well as their respective concentrations[1]. This work utilizes techniques from dimensionality reduction and linear decompositions to present a more accurate model using data from the European Massbank Metabolome Library to produce a global list of chemicals that researchers can then identify and test for when purifying water., 12 pages, 24 figures

International audience; Plug-and-Play priors recently emerged as a powerful technique for solving inverse problems by plugging a denoiser into a classical optimization algorithm. The denoiser accounts for the regularization and therefore implicitly determines the prior knowledge on the data, hence replacing typical handcrafted priors. In this paper, we extend the concept of Plug-and-Play priors to use denoisers that can be parameterized for non-constant noise variance. In that aim, we introduce a preconditioning of the ADMM algorithm, which mathematically justifies the use of such an adjustable denoiser. We additionally propose a procedure for training a convolutional neural network for high quality non-blind image denoising that also allows for pixel-wise control of the noise standard deviation. We show that our pixel-wise adjustable denoiser, along with a suitable preconditioning strategy, can further improve the Plug-and-Play ADMM approach for several applications, including image completion, interpolation, demosaicing and Poisson denoising.

The Plug-and-Play (PnP) framework makes it possible to integrate advanced image denoising priors into optimization algorithms, to efficiently solve a variety of image restoration tasks generally formulated as Maximum A Posteriori (MAP) estimation problems. The Plug-and-Play alternating direction method of multipliers (ADMM) and the Regularization by Denoising (RED) algorithms are two examples of such methods that made a breakthrough in image restoration. However, while the former method only applies to proximal algorithms, it has recently been shown that there exists no regularization that explains the RED algorithm when the denoisers lack Jacobian symmetry, which happen to be the case of most practical denoisers. To the best of our knowledge, there exists no method for training a network that directly represents the gradient of a regularizer, which can be directly used in Plug-and-Play gradient-based algorithms. We show that it is possible to train a network directly modeling the gradient of a MAP regularizer while jointly training the corresponding MAP denoiser. We use this network in gradient-based optimization methods and obtain better results comparing to other generic Plug-and-Play approaches. We also show that the regularizer can be used as a pre-trained network for unrolled gradient descent. Lastly, we show that the resulting denoiser allows for a better convergence of the Plug-and-Play ADMM.

The requirement to repeatedly move large feature maps off- and on-chip during inference with convolutional neural networks (CNNs) imposes high costs in terms of both energy and time. In this work we explore an improved method for compressing all feature maps of pre-trained CNNs to below a specified limit. This is done by means of learned projections trained via end-to-end finetuning, which can then be folded and fused into the pre-trained network. We also introduce a new `ceiling compression' framework in which evaluate such techniques in view of the future goal of performing inference fully on-chip.

With the advent of the digital era, every day-to-day task is automated due to technological advances. However, technology has yet to provide people with enough tools and safeguards. As the internet connects more-and-more devices around the globe, the question of securing the connected devices grows at an even spiral rate. Data thefts, identity thefts, fraudulent transactions, password compromises, and system breaches are becoming regular everyday news. The surging menace of cyber-attacks got a jolt from the recent advancements in Artificial Intelligence. AI is being applied in almost every field of different sciences and engineering. The intervention of AI not only automates a particular task but also improves efficiency by many folds. So it is evident that such a scrumptious spread would be very appetizing to cybercriminals. Thus the conventional cyber threats and attacks are now ``intelligent" threats. This article discusses cybersecurity and cyber threats along with both conventional and intelligent ways of defense against cyber-attacks. Furthermore finally, end the discussion with the potential prospects of the future of AI in cybersecurity., Submitted to Springer

Despite fluorescent cell-labelling being widely employed in biomedical studies, some of its drawbacks are inevitable, with unsuitable fluorescent probes or probes inducing a functional change being the main limitations. Consequently, the demand for and development of label-free methodologies to classify cells is strong and its impact on precision medicine is relevant. Towards this end, high-throughput techniques for cell mechanical phenotyping have been proposed to get a multidimensional biophysical characterization of single cells. With this motivation, our goal here is to investigate the extent to which an unsupervised machine learning methodology, which is applied exclusively on morpho-rheological markers obtained by real-time deformability and fluorescence cytometry (RT-FDC), can address the difficult task of providing label-free discrimination of reticulocytes from mature red blood cells. We focused on this problem, since the characterization of reticulocytes (their percentage and cellular features) in the blood is vital in multiple human disease conditions, especially bone-marrow disorders such as anemia and leukemia. Our approach reports promising label-free results in the classification of reticulocytes from mature red blood cells, and it represents a step forward in the development of high-throughput morpho-rheological-based methodologies for the computational categorization of single cells. Besides, our methodology can be an alternative but also a complementary method to integrate with existing cell-labelling techniques., 13 pages, 3 figures, 4 tables

Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to widen this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identifying the necessary components and characteristics to allow different adaptations of said model depending on the tasks it is required to fulfill. Secondly, employing the formal definition as a starting point, we develop an illustrative model example consisting of three different tasks (classification, regression and data sampling). The performance of this model implementation is then analyzed, showing its capabilities. Motivated by the results of the analysis, we enumerate a set of open challenges and future research lines over which the full potential of the proposed model definition can be exploited., Preprint

Score-based generative models (SGMs) need to approximate the scores $\nabla \log p_t$ of the intermediate distributions as well as the final distribution $p_T$ of the forward process. The theoretical underpinnings of the effects of these approximations are still lacking. We find precise conditions under which SGMs are able to produce samples from an underlying (low-dimensional) data manifold $\mathcal{M}$. This assures us that SGMs are able to generate the "right kind of samples". For example, taking $\mathcal{M}$ to be the subset of images of faces, we find conditions under which the SGM robustly produces an image of a face, even though the relative frequencies of these images might not accurately represent the true data generating distribution. Moreover, this analysis is a first step towards understanding the generalization properties of SGMs: Taking $\mathcal{M}$ to be the set of all training samples, our results provide a precise description of when the SGM memorizes its training data.

Decision diagrams for classification have some notable advantages over decision trees, as their internal connections can be determined at training time and their width is not bound to grow exponentially with their depth. Accordingly, decision diagrams are usually less prone to data fragmentation in internal nodes. However, the inherent complexity of training these classifiers acted as a long-standing barrier to their widespread adoption. In this context, we study the training of optimal decision diagrams (ODDs) from a mathematical programming perspective. We introduce a novel mixed-integer linear programming model for training and demonstrate its applicability for many datasets of practical importance. Further, we show how this model can be easily extended for fairness, parsimony, and stability notions. We present numerical analyses showing that our model allows training ODDs in short computational times, and that ODDs achieve better accuracy than optimal decision trees, while allowing for improved stability without significant accuracy losses.

Dengue is a mosquito-borne pandemic viral infection, which transmits to humans from Female Aedes albopictis or Aedes agypti mosquitoes. It progressively deteriorates the health of infected individuals and poses a high threat of human morbidity and mortality. This paper proposes an intelligent healthcare system which identifies, monitors, and alerts dengue virus (DeV) infected individuals and other stakeholders in real-time and control the DeV infection outbreak using cloud computing, internet of things and fog computing paradigms. The proposed system uses Naive Bayesian Network (NBN) for diagnosing the possibly DeV infected individuals and generating real-time alerts for suggesting and alerting the concerned stakeholders for taking on-time necessary actions at the fog subsystem. The proposed system also uses Social Network Analysis at the cloud subsystem, to provide Global Positioning Systems (GPS)-based global risk assessment of the DeV infection on Google Maps (Google-based web map service) and control DeV infection outbreak. The analysis of the experimental results acknowledges the efficiency of the NBN-based DeV infection diagnosis, alert generation, and GPS-based risk assessment functionality, of the proposed system, via various statistical measures and experimental approaches.

In this article, we formalize in Mizar a binary operationof points on an elliptic curve overGF(p) in affine coordinates. We show that theoperation is unital, complementable and commutative. Elliptic curve cryptogra-phy, whose security is based on a difficulty of discrete logarithm problem ofelliptic curves, is important for information security., Article, FORMALIZED MATHEMATICS 27(3) : 315-320(2020)

Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In this paper, we demonstrate blinding attacks that can fully disguise an ongoing attack against the machine learning model. Similar to neural backdoors, we modify the model's prediction upon trigger presence but simultaneously also fool the provided explanation. This enables an adversary to hide the presence of the trigger or point the explanation to entirely different portions of the input, throwing a red herring. We analyze different manifestations of such attacks for different explanation types in the image domain, before we resume to conduct a red-herring attack against malware classification.

In this paper, we present CrudeOilNews, a corpus of English Crude Oil news for event extraction. It is the first of its kind for Commodity News and serve to contribute towards resource building for economic and financial text mining. This paper describes the data collection process, the annotation methodology and the event typology used in producing the corpus. Firstly, a seed set of 175 news articles were manually annotated, of which a subset of 25 news were used as the adjudicated reference test set for inter-annotator and system evaluation. Agreement was generally substantial and annotator performance was adequate, indicating that the annotation scheme produces consistent event annotations of high quality. Subsequently the dataset is expanded through (1) data augmentation and (2) Human-in-the-loop active learning. The resulting corpus has 425 news articles with approximately 11k events annotated. As part of active learning process, the corpus was used to train basic event extraction models for machine labeling, the resulting models also serve as a validation or as a pilot study demonstrating the use of the corpus in machine learning purposes. The annotated corpus is made available for academic research purpose at https://github.com/meisin/CrudeOilNews-Corpus., Comment: Accepted at LREC 2022. arXiv admin note: text overlap with arXiv:2105.08214

Hierarchical models represent a challenging setting for inference algorithms. MCMC methods struggle to scale to large models with many local variables and observations, and variational inference (VI) may fail to provide accurate approximations due to the use of simple variational families. Some variational methods (e.g. importance weighted VI) integrate Monte Carlo methods to give better accuracy, but these tend to be unsuitable for hierarchical models, as they do not allow for subsampling and their performance tends to degrade for high dimensional models. We propose a new family of variational bounds for hierarchical models, based on the application of tightening methods (e.g. importance weighting) separately for each group of local random variables. We show that our approach naturally allows the use of subsampling to get unbiased gradients, and that it fully leverages the power of methods that build tighter lower bounds by applying them independently in lower dimensional spaces, leading to better results and more accurate posterior approximations than relevant baselines., Presented at ICML 2022

Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical. Adding differential privacy guarantees bounds on privacy while data are contributed to a global model. Adding personalization to federated learning introduces new challenges as we must account for preferences of individual users, where a data sample could have conflicting labels because one sub-population of users might view an input positively, but other sub-populations view the same input negatively. We present FedEmbed, a new approach to private federated learning for personalizing a global model that uses (1) sub-populations of similar users, and (2) personal embeddings. We demonstrate that current approaches to federated learning are inadequate for handling data with conflicting labels, and we show that FedEmbed achieves up to 45% improvement over baseline approaches to personalized private federated learning., 15 pages

Structured access is an emerging paradigm for the safe deployment of artificial intelligence (AI). Instead of openly disseminating AI systems, developers facilitate controlled, arm's length interactions with their AI systems. The aim is to prevent dangerous AI capabilities from being widely accessible, whilst preserving access to AI capabilities that can be used safely. The developer must both restrict how the AI system can be used, and prevent the user from circumventing these restrictions through modification or reverse engineering of the AI system. Structured access is most effective when implemented through cloud-based AI services, rather than disseminating AI software that runs locally on users' hardware. Cloud-based interfaces provide the AI developer greater scope for controlling how the AI system is used, and for protecting against unauthorized modifications to the system's design. This chapter expands the discussion of "publication norms" in the AI community, which to date has focused on the question of how the informational content of AI research projects should be disseminated (e.g., code and models). Although this is an important question, there are limits to what can be achieved through the control of information flows. Structured access views AI software not only as information that can be shared but also as a tool with which users can have arm's length interactions. There are early examples of structured access being practiced by AI developers, but there is much room for further development, both in the functionality of cloud-based interfaces and in the wider institutional framework., Comment: 28 pages

Differential Privacy (DP) is a formal definition of privacy that provides rigorous guarantees against risks of privacy breaches during data processing. It makes no assumptions about the knowledge or computational power of adversaries, and provides an interpretable, quantifiable and composable formalism. DP has been actively researched during the last 15 years, but it is still hard to master for many Machine Learning (ML)) practitioners. This paper aims to provide an overview of the most important ideas, concepts and uses of DP in ML, with special focus on its intersection with Federated Learning (FL)., Comment: 27 pages, 7 figures

Causal discovery has become a vital tool for scientists and practitioners wanting to discover causal relationships from observational data. While most previous approaches to causal discovery have implicitly assumed that no expert domain knowledge is available, practitioners can often provide such domain knowledge from prior experience. Recent work has incorporated domain knowledge into constraint-based causal discovery. The majority of such constraint-based methods, however, assume causal faithfulness, which has been shown to be frequently violated in practice. Consequently, there has been renewed attention towards exact-search score-based causal discovery methods, which do not assume causal faithfulness, such as A*-based methods. However, there has been no consideration of these methods in the context of domain knowledge. In this work, we focus on efficiently integrating several types of domain knowledge into A*-based causal discovery. In doing so, we discuss and explain how domain knowledge can reduce the graph search space and then provide an analysis of the potential computational gains. We support these findings with experiments on synthetic and real data, showing that even small amounts of domain knowledge can dramatically speed up A*-based causal discovery and improve its performance and practicality.

Power electronics converters have been widely used in aerospace system, DC transmission, distributed energy, smart grid and so forth, and the reliability of power electronics converters has been a hotspot in academia and industry. It is of great significance to carry out power electronics converters open-circuit faults monitoring and intelligent fault diagnosis to avoid secondary faults, reduce time and cost of operation and maintenance, and improve the reliability of power electronics system. Firstly, the faults features of power electronic converters are analyzed and summarized. Secondly, some AI-based fault diagnosis methods and application examples in power electronics converters are reviewed, and a fault diagnosis method based on the combination of random forests and transient fault features is proposed for three-phase power electronics converters. Finally, the future research challenges and directions of AI-based fault diagnosis methods are pointed out., Comment: Power System Technology

Explainable Artificial Intelligence (XAI) research gained prominence in recent years in response to the demand for greater transparency and trust in AI from the user communities. This is especially critical because AI is adopted in sensitive fields such as finance, medicine etc., where implications for society, ethics, and safety are immense. Following thorough systematic evaluations, work in XAI has primarily focused on Machine Learning (ML) for categorization, decision, or action. To the best of our knowledge, no work is reported that offers an Explainable Reinforcement Learning (XRL) method for trading financial stocks. In this paper, we proposed to employ SHapley Additive exPlanation (SHAP) on a popular deep reinforcement learning architecture viz., deep Q network (DQN) to explain an action of an agent at a given instance in financial stock trading. To demonstrate the effectiveness of our method, we tested it on two popular datasets namely, SENSEX and DJIA, and reported the results., Comment: 28 pages; 3 Tables; 21 Figures

Retrosynthesis is a major task for drug discovery. It is formulated as a graph-generating problem by many existing approaches. Specifically, these methods firstly identify the reaction center, and break target molecule accordingly to generate synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or directly adding proper leaving groups. However, both two strategies suffer since adding atoms results in a long prediction sequence which increases generation difficulty, while adding leaving groups can only consider the ones in the training set which results in poor generalization. In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants. Since chemically meaningful motifs are bigger than atoms and smaller than leaving groups, our method enjoys lower prediction complexity than adding atoms and better generalization than adding leaving groups. Experiments on a benchmark dataset show that the proposed model significantly outperforms previous state-of-the-art algorithms., Comment: 16 pages, 3 figures

Cybersecurity is the security cornerstone of digital transformation of the power grid and construction of new power systems. The traditional network security situation quantification method only analyzes from the perspective of network performance, ignoring the impact of various power application services on the security situation, so the quantification results cannot fully reflect the power information network risk state. This study proposes a method for quantifying security situation of the power information network based on the evolutionary neural network. First, the security posture system architecture is designed by analyzing the business characteristics of power information network applications. Second, combining the importance of power application business, the spatial element index system of coupled interconnection is established from three dimensions of network reliability, threat, and vulnerability. Then, the BP neural network optimized by the genetic evolutionary algorithm is incorporated into the element index calculation process, and the quantitative model of security posture of the power information network based on the evolutionary neural network is constructed. Finally, a simulation experiment environment is built according to a power sector network topology, and the effectiveness and robustness of the method proposed in the study are verified., Comment: Frontiers in Energy Research

The criteria for measuring music similarity are important for developing a flexible music recommendation system. Some data-driven methods have been proposed to calculate music similarity from only music signals, such as metric learning based on a triplet loss using tag information on each musical piece. However, the resulting music similarity metric usually captures the entire piece of music, i.e., the mixing of various instrumental sound sources, limiting the capability of the music recommendation system, e.g., it is difficult to search for a musical piece containing similar drum sounds. Towards the development of a more flexible music recommendation system, we propose a music similarity calculation method that focuses on individual instrumental sound sources in a musical piece. By fully exploiting the potential of data-driven methods for our proposed method, we employ weakly supervised metric learning to individual instrumental sound source signals without using any tag information, where positive and negative samples in a triplet loss are defined by whether or not they are from the same musical piece. Furthermore, assuming that each instrumental sound source is not always available in practice, we also investigate the effects of using instrumental sound source separation to obtain each source in the proposed method. Experimental results have shown that (1) unique similarity metrics can be learned for individual instrumental sound sources, (2) similarity metrics learned using some instrumental sound sources are possible to lead to more accurate results than that learned using the entire musical piece, (3) the performance degraded when learning with the separated instrumental sounds, and (4) similarity metrics learned by the proposed method well produced results that correspond to perception by human senses., Comment: APSIPA ASC 2022 (pp.33--38)

A three-phase pulse-width modulation (PWM) rectifier can usually maintain operation when open-circuit faults occur in insulated-gate bipolar transistors (IGBTs), which will lead the system to be unstable and unsafe. Aiming at this problem, based on random forests with transient synthetic features, a data-driven online fault diagnosis method is proposed to locate the open-circuit faults of IGBTs timely and effectively in this study. Firstly, by analysing the open-circuit fault features of IGBTs in the three-phase PWM rectifier, it is found that the occurrence of the fault features is related to the fault location and time, and the fault features do not always appear immediately with the occurrence of the fault. Secondly, different data-driven fault diagnosis methods are compared and evaluated, the performance of random forests algorithm is better than that of support vector machine or artificial neural networks. Meanwhile, the accuracy of fault diagnosis classifier trained by transient synthetic features is higher than that trained by original features. Also, the random forests fault diagnosis classifier trained by multiplicative features is the best with fault diagnosis accuracy can reach 98.32%. Finally, the online fault diagnosis experiments are carried out and the results demonstrate the effectiveness of the proposed method, which can accurately locate the open-circuit faults in IGBTs while ensuring system safety., Comment: IET Power Electronics

Audio-visual correlation learning aims to capture essential correspondences and understand natural phenomena between audio and video. With the rapid growth of deep learning, an increasing amount of attention has been paid to this emerging research issue. Through the past few years, various methods and datasets have been proposed for audio-visual correlation learning, which motivate us to conclude a comprehensive survey. This survey paper focuses on state-of-the-art (SOTA) models used to learn correlations between audio and video, but also discusses some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate some objective functions frequently used for optimizing audio-visual correlation learning models and discuss how audio-visual data is exploited in the optimization process. Most importantly, we provide an extensive comparison and summarization of the recent progress of SOTA audio-visual correlation learning and discuss future research directions., Comment: 8 pages, 1 figure

Achieving maximum possible rate of inferencing with minimum hardware resources plays a major role in reducing enterprise operational costs. In this paper we explore use of PCIe streaming on FPGA based platforms to achieve high throughput. PCIe streaming is a unique capability available on FPGA that eliminates the need for memory copy overheads. We have presented our results for inferences on a gradient boosted trees model, for online retail recommendations. We compare the results achieved with the popular library implementations on GPU and the CPU platforms and observe that the PCIe streaming enabled FPGA implementation achieves the best overall measured performance. We also measure power consumption across all platforms and find that the PCIe streaming on FPGA platform achieves the 25x and 12x better energy efficiency than an implementation on CPU and GPU platforms, respectively. We discuss the conditions that need to be met, in order to achieve this kind of acceleration on the FPGA. Further, we analyze the run time statistics on GPU and FPGA and identify opportunities to enhance performance on both the platforms.

Ensemble Learning methods combine multiple algorithms performing the same task to build a group with superior quality. These systems are well adapted to the distributed setup, where each peer or machine of the network hosts one algorithm and communicate its results to its peers. Ensemble learning methods are naturally resilient to the absence of several peers thanks to the ensemble redundancy. However, the network can be corrupted, altering the prediction accuracy of a peer, which has a deleterious effect on the ensemble quality. In this paper, we propose a noise-resilient ensemble classification method, which helps to improve accuracy and correct random errors. The approach is inspired by Evidence Accumulation Clustering , adapted to classification ensembles. We compared it to the naive voter model over four multi-class datasets. Our model showed a greater resilience, allowing us to recover prediction under a very high noise level. In addition as the method is based on the evidence accumulation clustering, our method is highly flexible as it can combines classifiers with different label definitions., Comment: 12 pages, submitted and accepted to ANTIC-2021 (International Conference on Advanced Network Technologies and Intelligent Computing)

Tags are short sequences of words allowing to describe textual and non-texual resources such as as music, image or book. Tags could be used by machine information retrieval systems to access quickly a document. These tags can be used to build recommender systems to suggest similar items to a user. However, the number of tags per document is limited, and often distributed according to a Zipf law. In this paper, we propose a methodology to cluster tags into conceptual groups. Data are preprocessed to remove power-law effects and enhance the context of low-frequency words. Then, a hierarchical agglomerative co-clustering algorithm is proposed to group together the most related tags into clusters. The capabilities were evaluated on a sparse synthetic dataset and a real-world tag collection associated with scientific papers. The task being unsupervised, we propose some stopping criterion for selectecting an optimal partitioning., Comment: 15 pages, submitted and accepted to the 2021 World Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE'21) - track ICAI21

We define the notion of a Ricci curvature lower bound for parametrized statistical models. Following the seminal ideas of Lott–Sturm–Villani, we define this notion based on the geodesic convexity of the Kullback–Leibler divergence in a Wasserstein statistical manifold, that is, a manifold of probability distributions endowed with a Wasserstein metric tensor structure. Within these definitions, which are based on Fisher information matrix and Wasserstein Christoffel symbols, the Ricci curvature is related to both, information geometry and Wasserstein geometry. These definitions allow us to formulate bounds on the convergence rate of Wasserstein gradient flows and information functional inequalities in parameter space. We discuss examples of Ricci curvature lower bounds and convergence rates in exponential family models.

Summary Rough sets, developed by Pawlak [15], are important tool to describe situation of incomplete or partially unknown information. In this article, continuing the formalization of rough sets [12], we give the formal characterization of three rough inclusion functions (RIFs). We start with the standard one, κ£ , connected with Łukasiewicz [14], and extend this research for two additional RIFs: κ 1, and κ 2, following a paper by Gomolińska [4], [3]. We also define q-RIFs and weak q-RIFs [2]. The paper establishes a formal counterpart of [7] and makes a preliminary step towards rough mereology [16], [17] in Mizar [13].

Summary This is the third part of a four-article series containing a Mizar [3], [1], [2] formalization of Kronecker’s construction about roots of polynomials in field extensions, i.e. that for every field F and every polynomial p ∈ F [X]\F there exists a field extension E of F such that p has a root over E. The formalization follows Kronecker’s classical proof using F [X]/ as the desired field extension E [6], [4], [5]. In the first part we show that an irreducible polynomial p ∈ F [X]\F has a root over F [X]/. Note, however, that this statement cannot be true in a rigid formal sense: We do not have F ⊆ F [X]/ < p > as sets, so F is not a subfield of F [X]/, and hence formally p is not even a polynomial over F [X]/ < p >. Consequently, we translate p along the canonical monomorphism ϕ: F → F [X]/ and show that the translated polynomial ϕ (p) has a root over F [X]/. Because F is not a subfield of F [X]/ we construct in the second part the field (E \ ϕF)∪F for a given monomorphism ϕ: F → E and show that this field both is isomorphic to F and includes F as a subfield. In the literature this part of the proof usually consists of saying that “one can identify F with its image ϕF in F [X]/ and therefore consider F as a subfield of F [X]/”. Interestingly, to do so we need to assume that F ∩ E = ∅, in particular Kronecker’s construction can be formalized for fields F with F ∩ F [X] = ∅. Surprisingly, as we show in this third part, this condition is not automatically true for arbitrary fields F : With the exception of ℤ2 we construct for every field F an isomorphic copy F′ of F with F′ ∩ F′ [X] ≠ ∅. We also prove that for Mizar’s representations of ℤ n , ℚ and ℝ we have ℤ n ∩ ℤ n [X] = ∅, ℚ ∩ ℚ[X] = ∅ and ℝ ∩ ℝ[X] = ∅, respectively. In the fourth part we finally define field extensions: E is a field extension of F iff F is a subfield of E. Note, that in this case we have F ⊆ E as sets, and thus a polynomial p over F is also a polynomial over E. We then apply the construction of the second part to F [X]/ with the canonical monomorphism ϕ: F → F [X]/. Together with the first part this gives – for fields F with F ∩ F [X] = ∅ – a field extension E of F in which p ∈ F [X]\F has a root.

Summary In this articles adjacency-preserving mappings from a graph to another are formalized in the Mizar system [7], [2]. The generality of the approach seems to be largely unpreceeded in the literature to the best of the author’s knowledge. However, the most important property defined in the article is that of two graphs being isomorphic, which has been extensively studied. Another graph decorator is introduced as well.

Summary In this article the notion of the underlying simple graph of a graph (as defined in [8]) is formalized in the Mizar system [5], along with some convenient variants. The property of a graph to be without decorators (as introduced in [7]) is formalized as well to serve as the base of graph enumerations in the future.

Summary This is the fourth part of a four-article series containing a Mizar [3], [2], [1] formalization of Kronecker’s construction about roots of polynomials in field extensions, i.e. that for every field F and every polynomial p ∈ F [X]\F there exists a field extension E of F such that p has a root over E. The formalization follows Kronecker’s classical proof using F [X]/ as the desired field extension E [6], [4], [5]. In the first part we show that an irreducible polynomial p ∈ F [X]\F has a root over F [X]/. Note, however, that this statement cannot be true in a rigid formal sense: We do not have F ⊆ F [X]/ < p > as sets, so F is not a subfield of F [X]/, and hence formally p is not even a polynomial over F [X]/ < p >. Consequently, we translate p along the canonical monomorphism ϕ: F → F [X]/ and show that the translated polynomial ϕ (p) has a root over F [X]/. Because F is not a subfield of F [X]/ we construct in the second part the field (E \ ϕF)∪F for a given monomorphism ϕ: F → E and show that this field both is isomorphic to F and includes F as a subfield. In the literature this part of the proof usually consists of saying that “one can identify F with its image ϕF in F [X]/ and therefore consider F as a subfield of F [X]/”. Interestingly, to do so we need to assume that F ∩ E = ∅, in particular Kronecker’s construction can be formalized for fields F with F ∩ F [X] = ∅. Surprisingly, as we show in the third part, this condition is not automatically true for arbitrary fields F : With the exception of ℤ2 we construct for every field F an isomorphic copy F′ of F with F′ ∩ F′ [X] ≠ ∅. We also prove that for Mizar’s representations of ℤ n , ℚ and ℝ we have ℤ n ∩ ℤ n [X] = ∅, ℚ ∩ ℚ[X] = ∅ and ℝ ∩ ℝ[X] = ∅, respectively. In this fourth part we finally define field extensions: E is a field extension of F iff F is a subfield of E. Note, that in this case we have F ⊆ E as sets, and thus a polynomial p over F is also a polynomial over E. We then apply the construction of the second part to F [X]/ with the canonical monomorphism ϕ: F → F [X]/. Together with the first part this gives – for fields F with F ∩ F [X] = ∅ – a field extension E of F in which p ∈ F [X]\F has a root.

Summary In [6] partial graph mappings were formalized in the Mizar system [3]. Such mappings map some vertices and edges of a graph to another while preserving adjacency. While this general approach is appropriate for the general form of (multidi)graphs as introduced in [7], a more specialized version for graphs without parallel edges seems convenient. As such, partial vertex mappings preserving adjacency between the mapped verticed are formalized here.

Summary This is the first part of a four-article series containing a Mizar [3], [1], [2] formalization of Kronecker’s construction about roots of polynomials in field extensions, i.e. that for every field F and every polynomial p ∈ F [X]\F there exists a field extension E of F such that p has a root over E. The formalization follows Kronecker’s classical proof using F [X]/ as the desired field extension E [9], [4], [6]. In this first part we show that an irreducible polynomial p ∈ F [X]\F has a root over F [X]/. Note, however, that this statement cannot be true in a rigid formal sense: We do not have F ⊆ [X]/ < p > as sets, so F is not a subfield of F [X]/, and hence formally p is not even a polynomial over F [X]/ < p >. Consequently, we translate p along the canonical monomorphism ϕ: F → F [X]/ and show that the translated polynomial ϕ(p) has a root over F [X]/. Because F is not a subfield of F [X]/ we construct in the second part the field (E \ ϕF )∪F for a given monomorphism ϕ : F → E and show that this field both is isomorphic to F and includes F as a subfield. In the literature this part of the proof usually consists of saying that “one can identify F with its image ϕF in F [X]/ and therefore consider F as a subfield of F [X]/”. Interestingly, to do so we need to assume that F ∩ E =∅, in particular Kronecker’s construction can be formalized for fields F with F \ F [X] =∅. Surprisingly, as we show in the third part, this condition is not automatically true for arbitray fields F : With the exception of 𝕑2 we construct for every field F an isomorphic copy F ′ of F with F′ ∩ F′ [X] ≠∅. We also prove that for Mizar’s representations of 𝕑n, 𝕈 and 𝕉 we have 𝕑n ∩ 𝕑n[X] = ∅, 𝕈 ∩ 𝕈[X] = ∅and 𝕉 ∩ 𝕉[X] = ∅, respectively. In the fourth part we finally define field extensions: E is a field extension of F i F is a subfield of E. Note, that in this case we have F ⊆ E as sets, and thus a polynomial p over F is also a polynomial over E. We then apply the construction of the second part to F [X]/ with the canonical monomorphism ϕ : F → F [X]/. Together with the first part this gives - for fields F with F ∩ F [X] = ∅ - a field extension E of F in which p ∈ F [X]\F has a root.

Summary The article is the next in a series aiming to formalize the MDPR-theorem using the Mizar proof assistant [3], [6], [4]. We analyze four equations from the Diophantine standpoint that are crucial in the bounded quantifier theorem, that is used in one of the approaches to solve the problem. Based on our previous work [1], we prove that the value of a given binomial coefficient and factorial can be determined by its arguments in a Diophantine way. Then we prove that two products z = ∏ i = 1 x ( 1 + i ⋅ y ) , z = ∏ i = 1 x ( y + 1 - j ) , ( 0.1 ) $$z = \prod\limits_{i = 1}^x {\left( {1 + i \cdot y} \right),\,\,\,\,\,\,\,\,} z = \prod\limits_{i = 1}^x {\left( {y + 1 - j} \right),\,\,\,\,\,\,(0.1)} $$ where y > x are Diophantine. The formalization follows [10], Z. Adamowicz, P. Zbierski [2] as well as M. Davis [5].

Summary This article is the final step of our attempts to formalize the negative solution of Hilbert’s tenth problem. In our approach, we work with the Pell’s Equation defined in [2]. We analyzed this equation in the general case to show its solvability as well as the cardinality and shape of all possible solutions. Then we focus on a special case of the equation, which has the form x 2 − (a 2 − 1)y 2 = 1 [8] and its solutions considered as two sequences { x i ( a ) } i = 0 ∞ , { y i ( a ) } i = 0 ∞ $\left\{ {{x_i}(a)} \right\}_{i = 0}^\infty ,\left\{ {{y_i}(a)} \right\}_{i = 0}^\infty$ . We showed in [1] that the n-th element of these sequences can be obtained from lists of several basic Diophantine relations as linear equations, finite products, congruences and inequalities, or more precisely that the equation x = y i(a) is Diophantine. Following the post-Matiyasevich results we show that the equality determined by the value of the power function y = x z is Diophantine, and analogously property in cases of the binomial coe cient, factorial and several product [9]. In this article, we combine analyzed so far Diophantine relation using conjunctions, alternatives as well as substitution to prove the bounded quantifier theorem. Based on this theorem we prove MDPR-theorem that every recursively enumerable set is Diophantine, where recursively enumerable sets have been defined by the Martin Davis normal form. The formalization by means of Mizar system [5], [7], [4] follows [10], Z. Adamowicz, P. Zbierski [3] as well as M. Davis [6].

Summary In this article, using the Mizar system [2], [1], we discuss invertible operators on Banach spaces. In the first chapter, we formalized the theorem that denotes any operators that are close enough to an invertible operator are also invertible by using the property of Neumann series. In the second chapter, we formalized the continuity of an isomorphism that maps an invertible operator on Banach spaces to its inverse. These results are used in the proof of the implicit function theorem. We referred to [3], [10], [6], [7] in this formalization.

Summary In this article, using the Mizar system [5], [2], the isomorphisms from the space of multilinear operators are discussed. In the first chapter, two isomorphisms are formalized. The former isomorphism shows the correspondence between the space of multilinear operators and the space of bilinear operators. The latter shows the correspondence between the space of multilinear operators and the space of the composition of linear operators. In the last chapter, the above isomorphisms are extended to isometric mappings between the normed spaces. We referred to [6], [11], [9], [3], [10] in this formalization.