Search

The distributional reinforcement learning (RL) approach advocates for representing the complete probability distribution of the random return instead of only modelling its expectation. A distributional RL algorithm may be characterised by two main components, namely the representation of the distribution together with its parameterisation and the probability metric defining the loss. The present research work considers the unconstrained monotonic neural network (UMNN) architecture, a universal approximator of continuous monotonic functions which is particularly well suited for modelling different representations of a distribution. This property enables the efficient decoupling of the effect of the function approximator class from that of the probability metric. The research paper firstly introduces a methodology for learning different representations of the random return distribution (PDF, CDF and QF). Secondly, a novel distributional RL algorithm named unconstrained monotonic deep Q-network (UMDQN) is presented. To the authors' knowledge, it is the first distributional RL method supporting the learning of three, valid and continuous representations of the random return distribution. Lastly, in light of this new algorithm, an empirical comparison is performed between three probability quasi-metrics, namely the Kullback-Leibler divergence, Cramer distance, and Wasserstein distance. The results highlight the main strengths and weaknesses associated with each probability metric together with an important limitation of the Wasserstein distance., Comment: Research paper accepted for publication in the peer-reviewed Neurocomputing journal edited by Elsevier

Real-time bidding (RTB) has become a critical way of online advertising. In RTB, an advertiser can participate in bidding ad impressions to display its advertisements. The advertiser determines every impression's bidding price according to its bidding strategy. Therefore, a good bidding strategy can help advertisers improve cost efficiency. This paper focuses on optimizing a single advertiser's bidding strategy using reinforcement learning (RL) in RTB. Unfortunately, it is challenging to optimize the bidding strategy through RL at the granularity of impression due to the highly dynamic nature of the RTB environment. In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly. Specifically, we use the maximum entropy RL algorithm (Soft Actor-Critic) to optimize the adjustment factor generation policy at the impression-grained level. Finally, the empirical study on a public dataset demonstrates that the proposed bidding strategy has superior performance compared with the baselines.

Computational Ethology studies focused on human beings is usually referred as Human Activity Recognition (HAR). Specifically, this paper belongs to a line of work on the identification of broad cognitive activities that users carry out with computers. The keystone of this kind of systems is the noninvasive detection of the subject's gaze fixations in selected display areas. Noninvasiveness is ensured by using the conventional laptop cameras without additional illumination or tracking devices. The gaze ethograms, composed as sequences of gaze fixations, are the basis to identify the user activities. To determine the gaze fixation display areas with the highest accuracy, this paper explores the use of a transfer learning approach applied to several well-known deep learning network (DLN) architectures whose input is the eye area extracted from the face image,and output is the identification of the gaze fixation area in the computer screen. Two different datasets are created and used in the validation experiments. We report encouraging results that may allow the general use of the system. This work has been supported by FEDER funds through MINECO project TIN2017-85827-P. This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 777720. XinZhe Jin contributed some early computational experiences.

Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are computed through propagating and aggregating the neighboring node features with respect to the graph. By stacking to multiple layers, GNNs are able to capture the long-range dependencies among the data on the graph and thus bring performance improvements. To train a GNN with multiple layers effectively, some normalization techniques (e.g., node-wise normalization, batch-wise normalization) are necessary. However, the normalization techniques for GNNs are highly task-relevant and different application tasks prefer to different normalization techniques, which is hard to know in advance. To tackle this deficiency, in this paper, we propose to learn graph normalization by optimizing a weighted combination of normalization techniques at four different levels, including node-wise normalization, adjacency-wise normalization, graph-wise normalization, and batch-wise normalization, in which the adjacency-wise normalization and the graph-wise normalization are newly proposed in this paper to take into account the local structure and the global structure on the graph, respectively. By learning the optimal weights, we are able to automatically select a single best or a best combination of multiple normalizations for a specific task. We conduct extensive experiments on benchmark datasets for different tasks, including node classification, link prediction, graph classification and graph regression, and confirm that the learned graph normalization leads to competitive results and that the learned weights suggest the appropriate normalization techniques for the specific task. Source code is released here https://github.com/cyh1112/GraphNormalization., Comment: 15 pages, 3 figures, 6 tables

In this paper, we present an extensive review on deep learning methods for image restoration tasks. Deep learning techniques, led by convolutional neural networks, have received a great deal of attention in almost all areas of image processing, especially in image classification. However, image restoration is a fundamental and challenging topic and plays significant roles in image processing, understanding and representation. It typically addresses image deblurring, denoising, dehazing and super-resolution. There are substantial differences in the approaches and mechanisms in deep learning methods for image restoration. Discriminative learning based methods are able to deal with issues of learning a restoration mapping function effectively, while optimisation models based methods can further enhance the performance with certain learning constraints. In this paper, we offer a comparative study of deep learning techniques in image denoising, deblurring, dehazing, and super-resolution, and summarise the principles involved in these tasks from various supervised deep network architectures, residual or skip connection and receptive field to unsupervised autoencoder mechanisms. Image quality criteria are also reviewed and their roles in image restoration are assessed. Based on our analysis, we further present an efficient network for deblurring and a couple of multi-objective training functions for super-resolution restoration tasks. The proposed methods are compared extensively with the state-of-the-art methods with both quantitative and qualitative analyses. Finally, we point out potential challenges and directions for future research.

In this paper, we propose a control framework for intelligent surgical robots under the Remote Center of Motion (RCM). The goal of a surgical robot is to assist surgeons in performing complex surgeries. RCM constraint implies that the surgical tip attached to the end-effector of the surgical robot does not slide away from the point of the incision while performing surgery. Implementation of a control algorithm to comply with RCM constraints is a complicated task because of the nonlinear model of the surgical robots and stringent conditions of accuracy imposed by the patient’s safety. This paper proposes an optimization-driven approach to perform the surgical maneuver under RCM constraints. We then applied a bio-inspired optimization algorithm to solve the problem efficiently. For testing the performance of ZNNBAS, we used MATLAB to simulate a surgical procedure. A 7-DOF surgical robot (KUKA LBR IIWA 7) was used as a test bench for running the simulations. The simulation results show that the ZNNBAS is comparable with BAS, PSO, and GA and efficiently and robustly performed the task commanded maneuvers while enforcing the RCM constraints.

Quite often a machine learning problem lends itself to be split in several well-defined subproblems, or tasks. The goal of Multi-Task Learning (MTL) is to leverage the joint learning of the problem from two different perspectives: on the one hand, a single, overall model, and on the other hand task-specific models. In this way, the found solution by MTL may be better than those of either the common or the task-specific models. Starting with the work of Evgeniou et al., support vector machines (SVMs) have lent themselves naturally to this approach. This paper proposes a convex formulation of MTL for the L1-, L2- and LS-SVM models that results in dual problems quite similar to the single-task ones, but with multi-task kernels; in turn, this makes possible to train the convex MTL models using standard solvers. As an alternative approach, the direct optimal combination of the already trained common and task-specific models can also be considered. In this paper, a procedure to compute the optimal combining parameter with respect to four different error functions is derived. As shown experimentally, the proposed convex MTL approach performs generally better than the alternative optimal convex combination, and both of them are better than the straight use of either common or task-specific models, With partial support from Spain’s grant TIN2016-76406-P. Work supported also by the UAM–ADIC Chair for Data Science and Machine Learning.

In the process of Human-robot skill transfer, we require the robot to reproduce the trajectory of teacher and expect that the robot can generalize the learned trajectory. For the trajectory after generalization, we expect that the robot arm can accurately track. However, because the model of the robot can not be accurately obtained, some researchers have proposed using a neural network to approximate the unknown term. The parameters of the traditional RBF neural network are usually selected through the empirical and trial-and-error method, which maybe biased and inefficient. In addition, due to the end-effector of the mechanical arm trajectory will be constantly changing according to the needs of the task, when the neural network of compact set cannot contain the whole input vector, the neural network cannot achieve the ideal approximation effect. In this paper, the broad neural network is used to approximate the unknown terms of the robot. This method can reuse the motion controller that has been learned and complete other motions in the robot operating space without relearning its weight parameters. In this paper, the effectiveness of the proposed method is proved by the ultrasound scanning task.

This paper proposes a hybrid architecture based on neural networks, fuzzy systems, and n-uninorms for solving pattern classification problems, termed as ENFS-Uni0 (short for evolving neuro-fuzzy system based on uni-nullneurons). The model can produce knowledge in an on-line (single-pass) and evolving learning context in a particular form of neuro-fuzzy rules representing the dependencies among input features through IF-THEN type relations. The rules antecedents are thereby realized through uni-nullneurons, which are constructed from n-uninorms, leading to the possibility to express both, AND- and OR-connections (and a mixture of these) among the single antecedent parts of a rule (and thus achieving an advanced interpretability aspect of the rules). The neurons’ evolution is done through an extended version of an autonomous data partition method (ADPA). On-line interpretation of the timely evolution of rules is addressed by (i) a concept for tracking the degree of changes of the rules over data stream samples, which may indicate experts/operators how much dynamics is in the process and may be used as a structural active learning component to request operator’s feedback in the case of significant changes and (ii) a concept for updating feature weights incrementally. These weights express the (possibly changing) impact degrees of features on the classification problem: features with low weights can be seen as unimportant and masked out when showing rules to an expert ( → rule length reduction). The rules’ consequents are represented by certainty vectors and are recursively updated by an indicator-based recursive weighted least squares (I-RWLS) approach (one RWLS estimator per class) where the weights are given through the neuron activation levels in order to gain stable local learning. The model proposed in this paper was successfully compared to related hybrid and evolving approaches in the literature for classifying binary and multi-class patterns. The results obtained by the proposed model show an outperformance of the related works in terms of higher accuracy trend lines over time, while offering a high degree of interpretability through coherent neuro-fuzzy rules to solve the classification problems.

Learning dynamics governed by differential equations is crucial for predicting and controlling the systems in science and engineering. Neural Ordinary Differential Equation (NODE), a deep learning model integrated with differential equations, is popular in learning dynamics recently due to its robustness to irregular samples and its flexibility to high-dimensional input. However, the training of NODE is sensitive to the precision of the numerical solver, which makes the convergence of NODE unstable, especially for ill-conditioned dynamical systems. In this paper, to reduce the reliance on the numerical solver, we propose to enhance the supervised signal in the training of NODE. Specifically, we pre-train a neural differential operator (NDO) to output an estimation of the derivatives to serve as an additional supervised signal. The NDO is pre-trained on a class of basis functions and learns the mapping between the trajectory samples of these functions to their derivatives. To leverage both the trajectory signal and the estimated derivatives from NDO, we propose an algorithm called NDO-NODE, in which the loss function contains two terms: the fitness on the true trajectory samples and the fitness on the estimated derivatives that are outputted by the pre-trained NDO. Experiments on various kinds of dynamics show that our proposed NDO-NODE can consistently improve the forecasting accuracy with one pre-trained NDO. Especially for the stiff ODEs, we observe that NDO-NODE can capture the transitions in the dynamics more accurately compared with other regularization methods., 19 pages, 12 figures, 4 tables

In this survey, kinship verification is defined as the automatic process of verifying whether two or more persons are blood relatives (kin) by analyzing images of their faces. Kinship verification is an important research field in computer vision with many applications such as finding missing persons, family album organization, and online image search. Although substantial progress has been made in kinship verification in the past decade, there are still challenges such as intrinsic (face i.e., differences in facial appearance) and extrinsic (acquisition i.e., varying imaging conditions) problems. And there is still a demand for more diverse datasets.Therefore, this paper provides a survey on kinship verification methods and datasets. The survey starts with the definition of kinship verification and its corresponding intrinsic and extrinsic challenges. Then, an overview of kinship verification methods and datasets is given. Finally, a new multi-modal dataset (Nemo-Kinship Dataset) is proposed as a benchmark dataset addressing large inter-subject age variations consisting of 4216 videos of 248 persons from 85 families. The newly collected dataset is used to systematically test and analyze state-of-the-art methods.

Learning and synthesizing stabilizing controllers for unknown nonlinear control systems is a challenging problem for real-world and industrial applications. Koopman operator theory allows one to analyze nonlinear systems through the lens of linear systems and nonlinear control systems through the lens of bilinear control systems. The key idea of these methods lies in the transformation of the coordinates of the nonlinear system into the Koopman observables, which are coordinates that allow the representation of the original system (control system) as a higher dimensional linear (bilinear control) system. However, for nonlinear control systems, the bilinear control model obtained by applying Koopman operator based learning methods is not necessarily stabilizable. Simultaneous identification of stabilizable lifted bilinear control systems as well as the associated Koopman observables is still an open problem. In this paper, we propose a framework to construct these stabilizable bilinear models and identify its associated observables from data by simultaneously learning a bilinear Koopman embedding for the underlying unknown control affine nonlinear system as well as a Control Lyapunov Function (CLF) for the Koopman based bilinear model using a learner and falsifier. Our proposed approach thereby provides provable guarantees of asymptotic stability for the Koopman based representation of the unknown control affine nonlinear control system as a bilinear system. Numerical simulations are provided to validate the efficacy of our proposed class of stabilizing feedback controllers for unknown control-affine nonlinear systems.

Identification and detection of thin-cap fibroatheroma (TCFA) from intravascular optical coherence tomography (IVOCT) images is critical for treatment of coronary heart diseases. Recently, deep learning methods have shown promising successes in TCFA identification. However, most methods usually do not effectively utilize multi-view information or incorporate prior domain knowledge. In this paper, we propose a multi-view contour-constrained transformer network (MVCTN) for TCFA identification in IVOCT images. Inspired by the diagnosis process of cardiologists, we use contour constrained self-attention modules (CCSM) to emphasize features corresponding to salient regions (i.e., vessel walls) in an unsupervised manner and enhance the visual interpretability based on class activation mapping (CAM). Moreover, we exploit transformer modules (TM) to build global-range relations between two views (i.e., polar and Cartesian views) to effectively fuse features at multiple feature scales. Experimental results on a semi-public dataset and an in-house dataset demonstrate that the proposed MVCTN outperforms other single-view and multi-view methods. Lastly, the proposed MVCTN can also provide meaningful visualization for cardiologists via CAM.

In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics. The integral reinforcement is measured as an excitation signal in this method to estimate the solution to the Hamilton-Jacobi-Bellman equation. Moreover, the proposed method is completely model-free, i.e. no a priori knowledge of the system is required. Using policy iteration, the actor and critic neural networks can simultaneously approximate the optimal value function and policy. The persistence of excitation condition is required to guarantee the convergence of the two networks. Unlike in traditional policy iteration algorithms, the restriction of the initial admissible policy is relaxed in this method. The effectiveness of the proposed algorithm is verified through numerical simulations.

Feature selection (FS) may improve the performance, cost-efficiency, and understandability of supervised machine learning models. In this paper, FS for the recently introduced distance-based supervised machine learning model is considered for regression problems. The study is contextualized by first providing an umbrella review (review of reviews) of recent development in the research field. We then propose a saliency-based one-shot wrapper algorithm for FS, which is called MAS-FS. The algorithm is compared with a set of other popular FS algorithms, using a versatile set of simulated and benchmark datasets. Finally, experimental results underline the usefulness of FS for regression, confirming the utility of certain filter algorithms and particularly the proposed wrapper algorithm. peerReviewed

Referring Expression Comprehension (REC) is one of the most important tasks in visual reasoning that requires a model to detect the target object referred by a natural language expression. Among the proposed pipelines, the one-stage Referring Expression Comprehension (OSREC) has become the dominant trend since it merges the region proposal and selection stages. Many state-of-the-art OSREC models adopt a multi-hop reasoning strategy because a sequence of objects is frequently mentioned in a single expression which needs multi-hop reasoning to analyze the semantic relation. However, one unsolved issue of these models is that the number of reasoning steps needs to be pre-defined and fixed before inference, ignoring the varying complexity of expressions. In this paper, we propose a Dynamic Multi-step Reasoning Network, which allows the reasoning steps to be dynamically adjusted based on the reasoning state and expression complexity. Specifically, we adopt a Transformer module to memorize & process the reasoning state and a Reinforcement Learning strategy to dynamically infer the reasoning steps. The work achieves the state-of-the-art performance or significant improvements on several REC datasets, ranging from RefCOCO (+, g) with short expressions, to Ref-Reasoning, a dataset with long and complex compositional expressions., 27 pages, 6 figures

Nonnegative matrix factorization (NMF) based topic modeling methods do not rely on model- or data-assumptions much. However, they are usually formulated as difficult optimization problems, which may suffer from bad local minima and high computational complexity. In this paper, we propose a deep NMF (DNMF) topic modeling framework to alleviate the aforementioned problems. It first applies an unsupervised deep learning method to learn latent hierarchical structures of documents, under the assumption that if we could learn a good representation of documents by, e.g. a deep model, then the topic word discovery problem can be boosted. Then, it takes the output of the deep model to constrain a topic-document distribution for the discovery of the discriminant topic words, which not only improves the efficacy but also reduces the computational complexity over conventional unsupervised NMF methods. We constrain the topic-document distribution in three ways, which takes the advantages of the three major sub-categories of NMF -- basic NMF, structured NMF, and constrained NMF respectively. To overcome the weaknesses of deep neural networks in unsupervised topic modeling, we adopt a non-neural-network deep model -- multilayer bootstrap network. To our knowledge, this is the first time that a deep NMF model is used for unsupervised topic modeling. We have compared the proposed method with a number of representative references covering major branches of topic modeling on a variety of real-world text corpora. Experimental results illustrate the effectiveness of the proposed method under various evaluation metrics.

Referring expression grounding is an important and challenging task in computer vision. To avoid the laborious annotation in conventional referring grounding, unpaired referring grounding is introduced, where the training data only contains a number of images and queries without correspondences. The few existing solutions to unpaired referring grounding are still preliminary, due to the challenges of learning image-text matching and lack of the top-down guidance with unpaired data. In this paper, we propose a novel bidirectional cross-modal matching (BiCM) framework to address these challenges. Particularly, we design a query-aware attention map (QAM) module that introduces top-down perspective via generating query-specific visual attention maps. A cross-modal object matching (COM) module is further introduced, which exploits the recently emerged image-text matching pretrained model, CLIP, to predict the target objects from a bottom-up perspective. The top-down and bottom-up predictions are then integrated via a similarity funsion (SF) module. We also propose a knowledge adaptation matching (KAM) module that leverages unpaired training data to adapt pretrained knowledge to the target dataset and task. Experiments show that our framework outperforms previous works by 6.55% and 9.94% on two popular grounding datasets., 9 pages, 7 figures

Graph neural networks (GNNs) have shown broad applicability in a variety of domains. These domains, e.g., social networks and product recommendations, are fertile ground for malicious users and behavior. In this paper, we show that GNNs are vulnerable to the extremely limited (and thus quite realistic) scenarios of a single-node adversarial attack, where the perturbed node cannot be chosen by the attacker. That is, an attacker can force the GNN to classify any target node to a chosen label, by only slightly perturbing the features or the neighbor list of another single arbitrary node in the graph, even when not being able to select that specific attacker node. When the adversary is allowed to select the attacker node, these attacks are even more effective. We demonstrate empirically that our attack is effective across various common GNN types (e.g., GCN, GraphSAGE, GAT, GIN) and robustly optimized GNNs (e.g., Robust GCN, SM GCN, GAL, LAT-GCN), outperforming previous attacks across different real-world datasets both in a targeted and non-targeted attacks. Our code is available at https://github.com/benfinkelshtein/SINGLE ., Comment: Appeared in Neurocomputing

Copyright © 2022 The Author(s). Online updating is an important statistical method for the analysis of big data arriving in streams due to its ability to break the storage barrier and the computational barrier under certain circumstances. The quantile regression, as a widely used regression model in many fields, faces challenges in model fitting and variable selection with big data arriving in streams. Chen et al. (2019, Annals of Statistics) has proposed a quantile regression method for streaming data, but a strong additional condition is required. In this paper, renewable optimized objective functions for regression parameter estimation and variable selection in a quantile regression are proposed. The proposed methods are illustrated using current data and the summary statistics of historical data. Theoretically, the proposed statistics are shown to have the same asymptotic distributions as the standard version computed on an entire data stream with the data batches pooled into one data set, without additional condition. Both simulations and data analysis are conducted to illustrate the finite sample performance of the proposed methods. This research is supported by the National Social Science Foundation of China (Series number: 21BTJ040)

This paper is intended to solve the fully distributed secure bipartite consensus problem of nonlinear multi-agent systems (MASs) with quantized information under Denial-of-Service (DoS) attacks. The attacks, which constrained on attack frequency and duration are studied. Firstly, we propose a novel secure output feedback control protocol integrated of the logarithmic quantizer and relative output measurements of neighboring agents, which can realize secure control under DoS attacks by choosing the design parameters correctly. Secondly, an adaptive control protocol that includes dynamic coupling strengths into the control law and the state observer function is developed. Contrast to the single adaptive control strategy, two adaptive couplings constructed in sensor-to-observer, and controller-to-actuator channels, respectively, which can alleviate the burden of the limited bandwidth and energy consumption more effectively. Furthermore, this control strategy with dynamic coupling gains is fully distributed, under which agents are not required to know a priori knowledge of any global information and the quantizer only needs to quantize the output state error information of agents. Then, theoretical guarantees on the effectiveness of the proposed controllers in steering the system to a secure bipartite (bounded) consensus under quantized output measurements and intermittent DoS attacks are derived. Finally, the numerical simulation inspired by a real-world physical network system is developed to verify the usefulness of the presented controllers.

3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks. In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover's Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.

Internet traffic recognition is an essential tool for access providers since recognizing traffic categories related to different data packets transmitted on a network help them define adapted priorities. That means, for instance, high priority requirements for an audio conference and low ones for a file transfer, to enhance user experience. As internet traffic becomes increasingly encrypted, the mainstream classic traffic recognition technique, payload inspection, is rendered ineffective. This paper uses machine learning techniques for encrypted traffic classification, looking only at packet size and time of arrival. Spiking neural networks (SNN), largely inspired by how biological neurons operate, were used for two reasons. Firstly, they are able to recognize time-related data packet features. Secondly, they can be implemented efficiently on neuromorphic hardware with a low energy footprint. Here we used a very simple feedforward SNN, with only one fully-connected hidden layer, and trained in a supervised manner using the newly introduced method known as Surrogate Gradient Learning. Surprisingly, such a simple SNN reached an accuracy of 95.9% on ISCX datasets, outperforming previous approaches. Besides better accuracy, there is also a very significant improvement on simplicity: input size, number of neurons, trainable parameters are all reduced by one to four orders of magnitude. Next, we analyzed the reasons for this good accuracy. It turns out that, beyond spatial (i.e. packet size) features, the SNN also exploits temporal ones, mostly the nearly synchronous (within a 200ms range) arrival times of packets with certain sizes. Taken together, these results show that SNNs are an excellent fit for encrypted internet traffic classification: they can be more accurate than conventional artificial neural networks (ANN), and they could be implemented efficiently on low power embedded systems., Comment: 22 pages, 8 figures. Neurocomputing (2022)

Due to the ever-increasing amount of various information provided by the internet, recommendation systems are now used in a large number of fields as efficient tools to get rid of information overload. The content-based, collaborative-based and hybrid methods are the three classical recommendation techniques, whereas not all real-world problems (e.g. the food recommendation problem) can be best addressed by such classical recommendation techniques. This paper is devoted to solving the food recommendation problem based on many-objective optimization (MaOO). A novel recommendation approach is proposed by transforming the original recommendation problem into an MaOO one that contains four different objectives, i.e., the user preferences, nutritional values, dietary diversity, and user diet patterns. The experimental results demonstrate that the designed recommendation approach provides a more balanced way of recommending food than the classical recommendation methods that only consider individuals’ food preferences.

Image deblurring is a fundamental and challenging low-level vision problem. Previous vision research indicates that edge structure in natural scenes is one of the most important factors to estimate the abilities of human visual perception. In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring. An edge detection convolutional subnet is designed in the first phase and a residual fully convolutional deblur subnet is then used for generating deblur results. The introduction of the edge-aware network enables our model with the specific capacity of enhancing images with sharp edges. We successfully apply our framework on standard benchmarks and promising results are achieved by our proposed deblur model.

As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation method for the point cloud data, named PointCutMix, to alleviate those problems. It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs. Two replacement strategies are proposed to adapt to the accuracy or robustness requirement for different tasks, one of which is to randomly select all replacing points while the other one is to select k nearest neighbors of a single random point. Both strategies consistently and significantly improve the performance of various models on point cloud classification problems. By introducing the saliency maps to guide the selection of replacing points, the performance further improves. Moreover, PointCutMix is validated to enhance the model robustness against the point attack. It is worth noting that when using as a defense method, our method outperforms the state-of-the-art defense algorithms. The code is available at:https://github.com/cuge1995/PointCutMix, Comment: 8 pages,5 figures

Rotating object detection has wide applications in aerial photographs, remote sensing images, UAVs, etc. At present, most of the rotating object detection datasets focus on the field of remote sensing, and these images are usually shot in high-altitude scenes. However, image datasets captured at low-altitude areas also should be concerned, such as drone-based datasets. So we present a low-altitude dronebased dataset, named UAV-ROD, aiming to promote the research and development in rotating object detection and UAV applications. The UAV-ROD consists of 1577 images and 30,090 instances of car category annotated by oriented bounding boxes. In particular, The UAV-ROD can be utilized for the rotating object detection, vehicle orientation recognition and object counting tasks. Compared with horizontal object detection, the regression stage of the rotation detection is a tricky problem. In this paper, we propose a rotating object detector TS4Net, which contains anchor refinement module (ARM) and two-stage sample selective strategy (TS4). The ARM can convert preseted horizontal anchors into high-quality rotated anchors through twostage anchor refinement. The TS4 module utilizes different constrained sample selective strategies to allocate positive and negative samples, which is adaptive to the regression task in different stages. Benefiting from the ARM and TS4, the TS4Net can achieve superior performance for rotating object detection solely with one preseted horizontal anchor. Extensive experimental results on UAV-ROD dataset and three remote sensing datasets DOTA, HRSC2016 and UCAS-AOD demonstrate that our method achieves competitive performance against most state-of-the-art methods., 12 pages, 11 figures

Existing online recruitment platforms depend on automatic ways of conducting the person-job fit, whose goal is matching appropriate job seekers with job positions. Intuitively, the previous successful recruitment records contain important information, which should be helpful for the current person-job fit. Existing studies on person-job fit, however, mainly focus on calculating the similarity between the candidate resumes and the job postings on the basis of their contents, without taking the recruiters' experience (i.e., historical successful recruitment records) into consideration. In this paper, we propose a novel neural network approach for person-job fit, which estimates person-job fit from candidate profile and related recruitment history with co-attention neural networks (named PJFCANN). Specifically, given a target resume-job post pair, PJFCANN generates local semantic representations through co-attention neural networks and global experience representations via graph neural networks. The final matching degree is calculated by combining these two representations. In this way, the historical successful recruitment records are introduced to enrich the features of resumes and job postings and strengthen the current matching process. Extensive experiments conducted on a large-scale recruitment dataset verify the effectiveness of PJFCANN compared with several state-of-the-art baselines. The codes are released at: https://github.com/CCIIPLab/PJFCANN.

Clustering is used in many applicative fields to summarize information into a small number of groups. Motivated by behavioral extraction issues from urban data, the interest of this paper is to propose a classification method that allows modeling the evolution of cluster profiles over time while considering common regressive effects. The parameters of the proposed model are estimated using variational approximation because maximum likelihood estimation is not suitable in this case. The ability of the model to estimate parameters is evaluated using various simulated data and compared with two other models.

While graph neural networks (GNNs) have shown a great potential in various tasks on graph, the lack of transparency has hindered understanding how GNNs arrived at its predictions. Although few explainers for GNNs are explored, the consideration of local fidelity, indicating how the model behaves around an instance should be predicted, is neglected. In this paper, we first propose a novel post-hoc framework based on local fidelity for any trained GNNs - TraP2, which can generate a high-fidelity explanation. Considering that both relevant graph structure and important features inside each node need to be highlighted, a three-layer architecture in TraP2 is designed: i) interpretation domain are defined by Translation layer in advance; ii) local predictive behavior of GNNs being explained are probed and monitored by Perturbation layer, in which multiple perturbations for graph structure and feature-level are conducted in interpretation domain; iii) high faithful explanations are generated by fitting the local decision boundary through Paraphrase layer. Finally, TraP2 is evaluated on six benchmark datasets based on five desired attributions: accuracy, fidelity, decisiveness, insight and inspiration, which achieves $10.2\%$ higher explanation accuracy than the state-of-the-art methods.

The overwhelming presence of categorical/sequential data in diverse domains emphasizes the importance of sequence mining. The challenging nature of sequences proves the need for continuing research to find a more accurate and faster approach providing a better understanding of their (dis)similarities. This paper proposes a new Model-based approach for clustering sequence data, namely nTreeClus. The proposed method deploys Tree-based Learners, k-mers, and autoregressive models for categorical time series, culminating with a novel numerical representation of the categorical sequences. Adopting this new representation, we cluster sequences, considering the inherent patterns in categorical time series. Accordingly, the model showed robustness to its parameter. Under different simulated scenarios, nTreeClus improved the baseline methods for various internal and external cluster validation metrics for up to 10.7% and 2.7%, respectively. The empirical evaluation using synthetic and real datasets, protein sequences, and categorical time series showed that nTreeClus is competitive or superior to most state-of-the-art algorithms., Comment: Published in Neurocomputing (Available online 22 April 2022)

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human cortex remains an academic challenge. It is critical to integrate properties of human vision into the design of CNN architectures, leading to perceptually more relevant saliency prediction. Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity. This hinders CNN-based saliency models from capturing properties that emulate viewing behaviour of humans. Transformers have shown great potential in encoding long-range information by leveraging the self-attention mechanism. In this paper, we propose a novel saliency model that integrates transformer components to CNNs to capture the long-range contextual visual information. Experimental results show that the transformers provide added value to saliency prediction, enhancing its perceptual relevance in the performance. Our proposed saliency model using transformers has achieved superior results on public benchmarks and competitions for saliency prediction models. The source code of our proposed saliency model TranSalNet is available at: https://github.com/LJOVO/TranSalNet, Comment: Source code: https://github.com/LJOVO/TranSalNet

While there exists a wide variety of graph neural networks (GNN) for node classification, only a minority of them adopt mechanisms that effectively target noise propagation during the message-passing procedure. Additionally, a very important challenge that significantly affects graph neural networks is the issue of scalability which limits their application to larger graphs. In this paper we propose our method named NODE-SELECT: an efficient graph neural network that uses subsetting layers which only allow the best sharing-fitting nodes to propagate their information. By having a selection mechanism within each layer which we stack in parallel, our proposed method NODE-SELECT is able to both reduce the amount noise propagated and adapt the restrictive sharing concept observed in real world graphs. Our NODE-SELECT significantly outperformed existing GNN frameworks in noise experiments and matched state-of-the art results in experiments without noise over different benchmark datasets.

Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulnerability of DL models stems from two factors. The first factor is data sparsity which is that in the high dimensional input data space, there exist large regions outside the support of the data distribution. The second factor is the existence of many redundant parameters in the DL models. Owing to these factors, different models are able to come up with different decision boundaries with comparably high prediction accuracy. The appearance of the decision boundaries in the space outside the support of the data distribution does not affect the prediction accuracy of the model. However, it makes an important difference in the adversarial robustness of the model. We hypothesize that the ideal decision boundary is as far as possible from the support of the data distribution. In this paper, we develop a training framework to observe if DL models are able to learn such a decision boundary spanning the space around the class distributions further from the data points themselves. Semi-supervised learning was deployed during training by leveraging unlabeled data generated in the space outside the support of the data distribution. We measured adversarial robustness of the models trained using this training framework against well-known adversarial attacks and by using robustness metrics. We found that models trained using our framework, as well as other regularization methods and adversarial training support our hypothesis of data sparsity and that models trained with these methods learn to have decision boundaries more similar to the aforementioned ideal decision boundary. The code for our training framework is available at https://github.com/MahsaPaknezhad/AdversariallyRobustTraining.

Online platforms have become an increasingly prominent means of communication. Despite the obvious benefits to the expanded distribution of content, the last decade has resulted in disturbing toxic communication, such as cyberbullying and harassment. Nevertheless, detecting online toxicity is challenging due to its multi-dimensional, context sensitive nature. As exposure to online toxicity can have serious social consequences, reliable models and algorithms are required for detecting and analyzing such communication across the vast and growing space of social media. In this paper, we draw on psychological and social theory to define toxicity. Then, we provide an approach that identifies multiple dimensions of toxicity and incorporates explicit knowledge in a statistical learning algorithm to resolve ambiguity across such dimensions.

This paper considers the leader-following bipartite consensus for a class of nonlinear multi-agent systems (MASs) subject to exogenous disturbances under directed fixed and switching topologies, respectively. Firstly, two new output feedback control protocols involving signs of link weights are introduced based on relative output measurements of neighboring agents. In order to estimate the disturbances produced by an exogenous system, a disturbance observer-based approach is developed. Then, sufficient conditions for leader-following bipartite consensus with directed fixed topologies are derived. Furthermore, by assuming that each switching topology contains a directed spanning tree, it is proved that the leader-following bipartite consensus can be realized with the designed output feedback control protocol if the dwell time is larger than a non-negative threshold. Finally, numerical simulations inspired by a real-world DC motors are provided to illustrate the effectiveness of the proposed controllers.

This paper proposes a novel reinforcement learning-based attitude tracking control strategy for combined spacecraft takeover maneuvers with completely unknown dynamics. One major issue in the context of combined spacecraft attitude takeover control is that the accurate dynamic model is highly nonlinear, complex and costly to identify online, which makes it impractical for control design. To address this issue, we take the advantage of the Q-learning algorithm to acquire the control strategy directly from system input/output measurement data in a model-free manner, and thus the online inertia parameter identification procedure is avoided. More specifically, first, the attitude tracking is formulated as a regulation problem by introducing an argumented system, where the system dynamic model is still required in control design. Then, in order to achieve a model-free control strategy, an online policy-iteration (PI) Q-learning procedure is derived to solve the Bellman optimality equation by utilizing the generated measurement data. In theoretical analysis, it is proved that the iteration sequences of Q value function and control strategy can converge to the optimal ones. In addition, rigorous proof of the stability and monotonicity guarantees of the proposed control strategy are also provided. Furthermore, for the purpose of online implementation, off-policy learning scheme is employed to find the optimal Q value function approximator with neural network structure after data-collection phase. Numerical simulations are exhibited to validate the effectiveness of the proposed strategy.

Despite many decades of research on high-performance Deep Neural Network (DNN) accelerators, their massive computational demand still requires resource-efficient, optimized and parallel architecture for computational acceleration. Contemporary hardware implementations of DNNs face the burden of excess area requirement due to resource-intensive elements such as multipliers and non-linear Activation Functions (AFs). This paper proposes DNN with reused hardware-costly AF by multiplexing data using shift-register. The on-chip quantized log 2 based memory addressing with an optimized technique is used to access input features, weights, and biases. This way the external memory bandwidth requirement is reduced and dynamically adjusted for DNNs. Further, high-throughput and resource-efficient memory elements for sigmoid activation function are extracted using the Taylor series and its order expansion have been tuned for better test accuracy. The performance is validated and compared with previous work for the MNIST dataset. Besides, the digital design of AF is synthesized at 45 nm technology node and physical parameters are compared with previous work. The proposed hardware reused architecture is verified for neural network 16:16:10:4 using 8-bit dynamic fixed-point arithmetic and implemented on Xilinx Zynq xc7z010clg400 SoC using 100 MHz clock. The implemented architecture uses 25% less hardware resources and consumes 12% less power without performance loss, compared to other state-of-the-art implementations, as lower hardware resources and power consumption are especially important for increasingly important edge computing solutions.

Generative models dealing with modeling a~joint data distribution are generally either autoencoder or GAN based. Both have their pros and cons, generating blurry images or being unstable in training or prone to mode collapse phenomenon, respectively. The objective of this paper is to construct a~model situated between above architectures, one that does not inherit their main weaknesses. The proposed LCW generator (Latent Cramer-Wold generator) resembles a classical GAN in transforming Gaussian noise into data space. What is of utmost importance, instead of a~discriminator, LCW generator uses kernel distance. No adversarial training is utilized, hence the name generator. It is trained in two phases. First, an autoencoder based architecture, using kernel measures, is built to model a manifold of data. We propose a Latent Trick mapping a Gaussian to latent in order to get the final model. This results in very competitive FID values.

Guided policy search algorithms have been proven to work with incredible accuracy not only for controlling complicated dynamical systems, but also in learning optimal policies from exploration of various unseen instances. This paper deals with a trajectory optimization problem for an unknown dynamical system subject to measurement noise using expectation maximization and extends it to learning (optimal) policies which have less stochasticity in trajectories because of the higher exploitation efficiency. Theoretical and empirical evidence of learned optimal policies for the new approach is depicted in comparison to some well known baselines which are evaluated on an autonomous system with widely used performance metrics.

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions. Submitted/Accepted version

Copyright © 2022 The Authors. In this paper, an explainable artificial intelligence (AI) technique is employed to analyze the match style and gameplay of the national basketball association (NBA). A descriptive analysis on the evolution of the NBA gameplay is conducted by using clustering and principal component analysis. Supervised-learning based AI models (including the random forest and the feed-forward neural network) are applied to produce accurate predictions on NBA outcomes at a season-by-season and a month-by-month basis. To evaluate the interpretability of the established AI models, an explainable AI algorithm is utilized to deduce and assess the precise reasoning behind the model prediction based on the local interpretable model-agnostic explanation method. To illustrate its application potential, the method is applied to the open-source NBA data from 1980 to 2019. Experimental results demonstrate the effectiveness of the introduced explainable AI algorithm on predicting NBA outcomes with interpretation.

The Covid-19 pandemic is the defining global health crisis of our time. Chest X-Rays (CXR) have been an important imaging modality for assisting in the diagnosis and management of hospitalised Covid-19 patients. However, their interpretation is time intensive for radiologists. Accurate computer aided systems can facilitate early diagnosis of Covid-19 and effective triaging. In this paper, we propose a fuzzy logic based deep learning (DL) approach to differentiate between CXR images of patients with Covid-19 pneumonia and with interstitial pneumonias not related to Covid-19. The developed model here, referred to as CovNNet, is used to extract some relevant features from CXR images, combined with fuzzy images generated by a fuzzy edge detection algorithm. Experimental results show that using a combination of CXR and fuzzy features, within a deep learning approach by developing a deep network inputed to a Multilayer Perceptron (MLP), results in a higher classification performance (accuracy rate up to 81%), compared to benchmark deep learning approaches. The approach has been validated through additional datasets which are continously generated due to the spread of the virus and would help triage patients in acute settings. A permutation analysis is carried out, and a simple occlusion methodology for explaining decisions is also proposed. The proposed pipeline can be easily embedded into present clinical decision support systems.

This paper presents a novel disturbance observer-based adaptive neural network control for a hydraulic knee exoskeleton with valve deadband and output constraint. Adaptive neural networks are employed to approximate the unknown nonlinearities of the hydraulic actuator, i.e., the valve deadband and the unmodeled dynamics caused by the valve leakage. A disturbance observer is designed and integrated into the controller to compensate for the external disturbance and the equivalent interactive force acted on the piston rod of the hydraulic actuator. Under the framwork of backstepping technique, both the state feedback and output feedback controllers of the exoskeleton are designed. The velocity of the piston rod is estimated via a high gain observer in the output feedback control design. By utilizing the barrier Lyapunov function method and the proposed control, the output constraints are handled and the semi-globally uniformly boundedness of the closed-loop system is also guaranteed. Comparative simulation results demonstrate the tracking performance of the proposed control approach.

Named Entity Recognition(NER), one of the most fundamental problems in natural language processing, seeks to identify the boundaries and types of entities with specific meanings in natural language text. As an important international language, Chinese has uniqueness in many aspects, and Chinese NER (CNER) is receiving increasing attention. In this paper, we give a comprehensive survey of recent advances in CNER. We first introduce some preliminary knowledge, including the common datasets, tag schemes, evaluation metrics and difficulties of CNER. Then, we separately describe recent advances in traditional research and deep learning research of CNER, in which the CNER with deep learning is our focus. We summarize related works in a basic three-layer architecture, including character representation, context encoder, and context encoder and tag decoder. Meanwhile, the attention mechanism and adversarial-transfer learning methods based on this architecture are introduced. Finally, we present the future research trends and challenges of CNER.

To understand animals’ behavior in finding relations between similar tasks and adapting themselves to changes in the tasks, it is necessary to know how the brain generalizes the learned knowledge from a previous task to unseen tasks. Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms. However, it is not known how such representation might help animals to manage uncertainty in their decision making. Existing methods for the SR learning based on standard temporal difference methods (e.g., deep neural network-based algorithms) do not capture uncertainty about the estimated SR. In order to address this issue, the paper presents a Kalman filter-based SR framework, referred to as Adaptive Kalman Filtering-based Successor Representation (AKF–SR). First, Kalman temporal difference approach, which is a combination of Kalman filter and the temporal difference method, is used within the AKF–SR framework to cast the SR learning procedure into a filtering problem to benefit from uncertainty estimation of the SR, and also decreases in memory requirement and sensitivity to model’s parameters in comparison to deep neural network-based algorithms. An adaptive Kalman filtering approach is then applied within the proposed AKF–SR framework in order to tune the measurement noise covariance and measurement mapping function of Kalman filter as the most important parameters affecting the filter’s performance. Moreover, an active learning method that exploits the estimated uncertainty of the SR to form the behaviour policy leading to more visits to less certain values is proposed to improve the overall performance of an agent in terms of received rewards while interacting with its environment. Experimental results based on three reinforcement learning environments illustrate the efficacy of the proposed AKF–SR framework over state-of-the-art frameworks in terms of cumulative reward, reliability, time and computational cost, and speed of convergence to changes in the reward function.

Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. The real-time speed is very important for the autonomous vehicle algorithms along with the accuracy metric. In this paper, we propose a semi-supervised real-time method based on the Siamese network using a new polar representation. The input of bounding boxes is initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea. The experimental results on the DAVIS-2016 dataset and other public datasets demonstrate the effectiveness of the proposed method., Comment: 11 pages, 11 figures, journal

Automatic plant classification is challenging due to the vast biodiversity of the existing plant species in a fine-grained scenario. Robust deep learning architectures have been used to improve the classification performance in such a fine-grained problem but usually build models that are highly dependent on a large training dataset and are not scalable. This paper proposes a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained plant species recognition. It uses the botanical taxonomy as a basis for a coarse-to-fine strategy applied to identify the plant genus and species. The two-view representation provides complementary global and local features of leaf images. A deep metric based on Siamese Convolutional Neural Networks is used to reduce the dependence on many training samples and make the method scalable to new plant species. The experimental results on two challenging fine-grained datasets of leaf images (i.e., PlantCLEF 2015 and LeafSnap) have shown the proposed method’s effectiveness, which achieved recognition accuracy of 0.87 and 0.96, respectively.

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a multi-scale input along with multiple domain adaptors applied hierarchically in both feature and output spaces. The proposed training strategy and novel unsupervised domain adaptation framework, called Collaborative Adversarial Domain Adaptation (CADA), can effectively overcome the challenge. Multi-scale inputs can reduce the information loss due to the pooling layers used in the network for feature extraction, while our proposed CADA is an interactive paradigm that presents an exquisite collaborative adaptation through both adversarial learning and ensembling weights at different network layers. In particular, to produce a better prediction for the unlabeled target domain data, we simultaneously achieve domain invariance and model generalizability via adversarial learning at multi-scale outputs from different levels of network layers and maintaining an exponential moving average (EMA) of the historical weights during training. Without annotating any sample from the target domain, multiple adversarial losses in encoder and decoder layers guide the extraction of domain-invariant features to confuse the domain classifier. Meanwhile, the ensembling of weights via EMA reduces the uncertainty of adapting multiple discriminator learning. Comprehensive experimental results demonstrate that our CADA model incorporating multi-scale input training can overcome performance degradation and outperform state-of-the-art domain adaptation methods in segmenting retinal optic disc and cup from fundus images stemming from the REFUGE, Drishti-GS, and Rim-One-r3 datasets., Comment: arXiv admin note: text overlap with arXiv:1910.07638