We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model. Conventional data-to-text model is useful when a reader seeks a global summary of data because it has only to describe an important part that has been extracted beforehand. However, since it differs from users to users what they are interested in, it is necessary to develop

Network embedding aims to map the topological proximities of all nodes in a network into a low-dimensional representation space. Previous studies mainly focus on preserving the within-layer structure of the network (such as first-order proximities, second-order proximities, and community structure). However, many complex networks present a hierarchical organization, often in the form of a hierarchy

Chaotic systems are suitable for image encryption owing to their numerous intrinsic characteristics. However, chaotic maps and algorithmic structures employed in many existing chaos-based image encryption algorithms exhibit various shortcomings. To overcome these, in this study, we first construct a two-dimensional logistic tent modular map (2D-LTMM) and then develop a new colour image encryption algorithm

Network survivability is one of the key challenges that the Internet of Things (IoTs) has to deal with, and cascading failures are one of the main bottlenecks affecting the network survivability of the IoTs. In this work, we fully considered the real characteristics of IoTs systems (i.e., data aggregation and link heterogeneity), and proposed a realistic cascading model based on the layered architecture

Similar to binary and multi-class classifiers, one-class classifiers have to face the difficulty of ’curse of dimensionality’ when they are applied to deal with high-dimensional samples. As an efficient dimensionality reduction method, sparse coding tries to learn a set of over-complete bases to represent the given samples. It can effectively overcome the ’curse of dimensionality’ problem. However

In this paper, we propose a speed-up approach for subclass discriminant analysis and formulate a novel efficient multi-view solution to it. The speed-up approach is developed based on graph embedding and spectral regression approaches that involve eigendecomposition of the corresponding Laplacian matrix and regression to its eigenvectors. We show that by exploiting the structure of the between-class

An object can be consisting of various attributes, such as illuminance, appearance, shape, orientation, etc. Separately extract these attributes has enormous value in visual effects modeling, attribute-specific retrieval and recognition. Essentially, these attributes can be fairly abstract and thus need labels to extract. However, sometimes the labels of these attributes may not be available with training

Salient object detection based on deep learning has become one of the research hotspots in computer vision. How to effectively extract useful information is a key issue for saliency detection. Most of the existing methods integrate features extracted from convolutional neural networks indiscriminately. However, the features of different layers have different characteristics, not all of them are useful

In this paper, the finite-time stability (FTS) problems for a class of fractional order memristor-based neural network (FOMNN) with time delays are investigated. Based on the method of steps, set-valued mapping, the theory of differential inclusion and fractional order Gronwall inequality, a new delay dependent criterion for the FTS of FOMNN with time delays and the fractional order 0<μ<1 is derived

Among various Sound Event Detection (SED) systems, Recurrent Neural Networks (RNN), such as long short-term memory unit and gated recurrent unit, is used to capture temporal dependencies, but it is confined in its length of temporal dependencies, resulting in a failure to model sound events with long duration. What’s more, RNN is incapable to process datasets in parallel, leading to low efficiency

Point-of-interests (POIs) recommendations aim at recommending locations to users on social platforms by analyzing their histories or combining other information. At present, the different granularity of factors (i.e. time, geography and sociability) are not thoroughly studied in existing works. To deal with this problem, we propose a two-stage coarse-to-fine POI recommendation algorithm based on tensor

An important part of art history can be discovered through the visual information in monument facades. However, the analysis of this visual information, i.e, morphology and architectural elements, requires high expert knowledge. An automatic system for identifying the architectural style or detecting the architectural elements of a monument based on one image will certainly help improving our knowledge

In this paper, we address cross-domain multi-dimensional emotion regression through adversarial learning. This is done via a proper conduction of both dimensional and domanial adversarial learning. On the one hand, we conduct adversarial learning between emotion dimensions via a dimensional discriminator to achieve dimension-specific features through the attention mechanism for better determining dimensional

Although deep learning has achieved remarkable successes over the past years, few reports have been published about applying deep neural networks to Wireless Sensor Networks (WSNs) for image targets recognition where data, energy, computation resources are limited. In this work, a Cost-Effective Domain Generalization (CEDG) algorithm has been proposed to train an efficient network with minimum labor

Deep recurrent neural networks (RNN), such as LSTM, have many advantages over forward networks for nonlinear system modeling. However, the most used training method, backward propagation through time (BPTT), is very slow. In this paper, by separating the LSTM cell into forward and recurrent models, we give a faster training method than BPTT. The deep LSTM is modified by combining the deep RNN with

In recent decades, unmanned surface vehicles (USVs) are attracting increasing attention due to their underlying capability in autonomously undertaking complex maritime tasks in constrained environments. However, the autonomy level of USVs is still limited, especially when being deployed to conduct multiple tasks simultaneously. This paper, therefore, aims to improve USVs autonomy level by investigating

The Internet of Vehicles (IoV) can obtain traffic information through a large number of data collected by sensors. However, the lack of data, abnormal data, and other low-quality problems have seriously restricted the development and application of the IoV. To solve the problem of missing data in a large-scale road network, the previous research achievements show that tensor decomposition method has

This study presents a novel deep learning architecture for multi-class classification and localization of abnormalities in medical imaging illustrated through experiments on mammograms. The proposed network combines two learning branches. One branch is for region classification with a newly added normal-region class. Second branch is region detection branch for ranking regions relative to one another

Linear Temporal Logic over finite traces (LTLf) was proposed in 2013 and has attracted increasing interest around the AI community. Though the theoretic basis for LTLf has been thoroughly explored since that time, there are still few algorithmic tools that are able to provide an efficient reasoning strategy for LTLf. In this paper, we present a SAT-based framework for LTLf satisfiability checking,

The original kernel extreme learning machine (KELM) employs all training samples to construct hidden layer, thus avoiding the performance fluctuations caused by the ELM randomly assigning weights. However, excessive nodes will inevitably lead to structural redundancy, which hinders its application in systems with high real-time performance requirements but limited onboard storage and computing capacity

Functional Magnetic Resonance Imaging (fMRI), for many decades acts as a potential aiding method for diagnosing medical problems. Several successful machine learning algorithms have been proposed in literature to extract valuable knowledge from fMRI. One of these algorithms is the convolutional neural network (CNN) that competent with high capabilities for learning optimal abstractions of fMRI. This

A Technical Document (TD) is mainly composed by a set of modalities appropriately structured and associated. These modalities could be NL-text, block diagrams, formulas, tables, graphics, pictures etc. A deep understanding of a TD will be based on the synergistic understanding and associations of these modalities. This paper offers a novel methodology for the implementation of a holistic approach for

This paper presents a new hybrid concession mechanism for negotiating agents. It considers both the current concession behavior of the proposing agent and the concession offered by its opponent in the last counteroffer to create a new offer. The proposed mechanism is a kind of imitating offer generation tactic. The difference is that it uses the first order difference between the two last counteroffers

Multi-Agent Systems are susceptible to external disturbances, sensor failures or collapse of communication channel/media. Such failures disconnect the agent network and thereby hamper the consensus of the system. Quick recovery of consensus is vital to continue the normal operation of an agent-based system. However, only limited works in the past have investigated the problem of recovering the consensus

In this paper, we focus on the problem of change point detection in piecewise constant signals. This problem is central to several applications such as human activity analysis, speech or image analysis and anomaly detection in genetics. We present a novel window-sliding algorithm for an online change point detection. The proposed approach considers a local blanket of a global Markov Random Field (MRF)

A question answering system is a type of information retrieval that takes a question from a user in natural language as the input and returns the best answer to it as the output. In this paper, a medical question answering system in the Persian language is designed and implemented. During this research, a dataset of diseases and drugs is collected and structured. The proposed system includes three

In some circumstances, the performance of machine learning (ML) tasks are based on the quality of signal (data) that is processed in these tasks. Therefore, the pre-processing techniques, such as reconstruction and denoising methods, are important techniques in ML tasks. In reconstructed (estimated) method, the fused lasso algorithm with non-convex penalty function is an efficient method when the signal

Argument mining consists in the automatic identification of argumentative structures in texts. In this work we leverage existing discourse-level annotations to facilitate the identification of argumentative components and relations in scientific texts, which has been recognized as a particularly challenging task. We propose a new annotation schema and use it to augment a corpus of computational linguistics

This paper describes how knowledge bases can be represented in and reasoned with in natural logic. Natural logic is a regimented fragment of natural language possessing a well-defined logical semantics. As such, natural logic may be considered an attractive alternative among the various knowledge representation logics such as description logics. Our version of natural logic expands formal ontologies

ABSTRACT Improvement of prediction accuracy and early detection of the Alzheimer’s disease is becoming increasingly important for managing its impact on lives of affected patients. Many machine learning approaches have been applied to support the diagnosis and prediction of this illness. In this paper we propose an approach for improving the Alzheimer’s disease classification accuracy by using data

Employee churn (ECn) is a crucial problem for any organization that adversely affects its overall revenue and brand image. Many machine learning (ML) based systems have been developed to solve the ECn problem. However, they miss out on some essential issues such as employee categorization, category-wise churn prediction, and retention policy for effectively addressing the ECn problem. By considering

The development of flexible swarm robotics systems capable of adapting to the task and environmental changes is a serious challenge. The main motivations of Swarm robotics are decentralized control, stability, adaptivity, and flexibility. Usually, ad-hoc approaches are employed to design a controller capable of meeting the problem specifications. However, these methods cannot be easily verified, and

Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability. We propose a novel method based on evolutionary algorithms, that deals with both challenges by massively reducing the number of trainable parameters, whilst simultaneously retaining classification performance, and in some cases achieving

High-level classification algorithms focus on the interactions between instances. These produce a new form to evaluate and classify data. In this process, the core is the complex network building methodology because it determines the metrics to be used for classification. The current methodologies use variations of kNN to produce these graphs. However, this technique ignores some hidden pattern between

ABSTRACT Wearables provide great opportunities for improving personal health, but research challenges their capacity to evoke behavioral change effectively. Realizing the full potential of wearables requires a better understanding of users’ behavior change processes. Based on self-efficacy theory, we investigate how wearables influence users’ perceptions of their self-efficacy and subsequent health

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia. Recently, deep neural networks operating on labeled point clouds have shown promising results on supervised learning tasks like classification and segmentation. However

We introduce Unbalanced Sobolev Descent (USD), a particle descent algorithm for transporting a high dimensional source distribution to a target distribution that does not necessarily have the same mass. We define the Sobolev-Fisher discrepancy between distributions and show that it relates to advection-reaction transport equations and the Wasserstein-Fisher-Rao metric between distributions. USD transports

We propose a novel tree-based ensemble method named Selective Cascade of Residual ExtraTrees (SCORE). SCORE draws inspiration from representation learning, incorporates regularized regression with variable selection features, and utilizes boosting to improve prediction and reduce generalization errors. We also develop a variable importance measure to increase the explainability of SCORE. Our computer

Advances on signal, image and video generation underly major breakthroughs on generative medical imaging tasks, including Brain Image Synthesis. Still, the extent to which functional Magnetic Ressonance Imaging (fMRI) can be mapped from the brain electrophysiology remains largely unexplored. This work provides the first comprehensive view on how to use state-of-the-art principles from Neural Processing

Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifiers available, there is a growing need for understanding interpretability of a classifier necessitated by practical purposes such as to find the best diet recommendation for a diabetes patient. Inverse classification is a post

Reinforcement Learning algorithms require a large number of samples to solve complex tasks with sparse and delayed rewards. Complex tasks can often be hierarchically decomposed into sub-tasks. A step in the Q-function can be associated with solving a sub-task, where the expectation of the return increases. RUDDER has been introduced to identify these steps and then redistribute reward to them, thus

With the abundance of industrial datasets, imbalanced classification has become a common problem in several application domains. Oversampling is an effective method to solve imbalanced classification. One of the main challenges of existing oversampling methods is to accurately label the new synthetic samples. Inaccurate labels of synthetic samples would distort the distribution of the dataset and possibly

The Fr\'echet Inception Distance (FID) has been used to evaluate thousands of generative models. We present a novel algorithm, FastFID, which allows fast computation and backpropagation for FID. FastFID can efficiently (1) evaluate generative model *during* training and (2) construct adversarial examples for FID.

This work targets the identification of a class of models for hybrid dynamical systems characterized by nonlinear autoregressive exogenous (NARX) components, with finite-dimensional polynomial expansions, and by a Markovian switching mechanism. The estimation of the model parameters is performed under a probabilistic framework via Expectation Maximization, including submodel coefficients, hidden state

Outcome estimation of treatments for target individuals is an important foundation for decision making based on causal relations. Most existing outcome estimation methods deal with binary or multiple-choice treatments; however, in some applications, the number of treatments can be significantly large, while the treatments themselves have rich information. In this study, we considered one important

In large shipyards, the management of equipment, which are used for building a variety of ships, is critical. Because orders vary year to year, shipyard managers are required to determine methods to make the most of their limited resources. A particular difficulty that arises because of the nature and size of shipyards is the management of moving vehicles. In recent years, shipbuilding companies have

Nowadays, people start to use online reservation systems to plan their vacations since they have vast amount of choices available. Selecting when and where to go from this large-scale options is getting harder. In addition, sometimes consumers can miss the better options due to the wealth of information to be found on the online reservation systems. In this sense, personalized services such as recommender

Image normalization is a building block in medical image analysis. Conventional approaches are customarily utilized on a per-dataset basis. This strategy, however, prevents the current normalization algorithms from fully exploiting the complex joint information available across multiple datasets. Consequently, ignoring such joint information has a direct impact on the performance of segmentation algorithms

Finding and analyzing meaningful representations of data is the purpose of machine learning. The idea of representation learning is to extract representations from the data itself, e.g., by utilizing deep neural networks. In this work, we examine representation learning from a geometric perspective. Especially, we focus on the convexity of classes and clusters as a natural and desirable representation

We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication network between the workers is synchronized and can be modeled as a doubly-stochastic mixing matrix without having any master node. In our setup, the training data is distributed among the workers but is not shared in the

Various Neural Networks employ time-consuming matrix operations like matrix inversion. Many such matrix operations are faster to compute given the Singular Value Decomposition (SVD). Previous work allows using the SVD in Neural Networks without computing it. In theory, the techniques can speed up matrix operations, however, in practice, they are not fast enough. We present an algorithm that is fast

Hybrid system identification is a key tool to achieve reliable models of Cyber-Physical Systems from data. PieceWise Affine models guarantees universal approximation, local linearity and equivalence to other classes of hybrid system. Still, PWA identification is a challenging problem, requiring the concurrent solution of regression and classification tasks. In this work, we focus on the identification

Contrarily to humans who have the ability to recombine familiar expressions to create novel ones, modern neural networks struggle to do so. This has been emphasized recently with the introduction of the benchmark dataset "gSCAN" (Ruis et al. 2020), aiming to evaluate models' performance at compositional generalization in grounded language understanding. In this work, we challenge the gSCAN benchmark

In order to design a more potent and effective chemical entity, it is essential to identify molecular structures with the desired chemical properties. Recent advances in generative models using neural networks and machine learning are being widely used by many emerging startups and researchers in this domain to design virtual libraries of drug-like compounds. Although these models can help a scientist

It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to adjust the mixture distribution weights remains an open question. Moreover, most existing work on this topic focuses only on minimizing the error on the source domains

Neural Processes (NPs) are powerful and flexible models able to incorporate uncertainty when representing stochastic processes, while maintaining a linear time complexity. However, NPs produce a latent description by aggregating independent representations of context points and lack the ability to exploit relational information present in many datasets. This renders NPs ineffective in settings where

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed

Support Vector Data Description (SVDD) is a popular one-class classifiers for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature