Neurocomputing

Spoken language understanding (SLU) plays an indispensable role in the dialogue system. The traditional intention detection task is regarded as a classification problem where utterances are associated with pre-defined intents. However, ...

Recent years have witnessed the increasing attentions on human action recognition(HAR). Traditional methods are prone to explore the optimum spatiotemporal feature representation of human actions in video clips so as to achieve high ...

This paper investigates the problem of adaptive tracking control for multi-agent systems subject to output constraint and unknown hysteresis. Different from most existing results that use the barrier Lyapunov function and integral ...

The graph model is a reliable propagation mechanism in saliency detection, saliency value propagation diffusion results between any two nodes are determined merely by defining an effect affinity matrix. Most existing methods generally ...

Multi-view clustering, which utilizes the ample information provided by multiple sources to obtain better performance, has attracted much attention. However, existing clustering algorithms either have no ability to offer confidence for ...

In this paper, we develop a novel Joint Model Compression (referred to as JMC) method by combining structured pruning and dense knowledge distillation techniques to significantly compress original large language model into a deep ...

Aiming at tracking control with bounded torque inputs of the flexible-joint robot manipulators, we propose a generalized saturated adaptive controller based on backstepping control, singular perturbation decoupling and neural networks. ...

Differential privacy, a strict privacy notion, prevents the presence or absence of a single data from being identified. This paper proposes a novel average consensus algorithm to achieve differentially private average consensus on ...

In this paper, a neural network (NN)-based adaptive hybrid impedance control (AHIC) scheme is proposed for the electrically driven flexible-joint robotic manipulators (EDFJRM) with input saturation, where the hybrid impedance is ...

The traditional robust principal component analysis (RPCA) via decomposition into low-rank plus sparse matrices offers a powerful framework for a large variety of applications in computer vision. However, the reconstructed image ...

Building detection is a critically important task in the field of remote sensing and it is conducive to urban construction planning, disaster survey, shantytown modification, and emergency landing, it etc. However, few studies have ...

• A novel approach combining CycleGANs and Activation Maximization is demonstrated to be applicable for the task of classifier decision explanation.

Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over ...

Recently, Self-Attention Networks (SANs) have shown its flexibility in parallel computation and effectiveness of modeling both short- and long-term dependencies. However, SANs face two problems: 1) the weighted averaging inhibits ...

Using neural networks to address data-driven problems often entails dealing with uncertainties. However, the propagation of uncertainty through a network’s nonlinear layers is usually a bottleneck, since the existing techniques ...

To solve the time-varying underdetermined linear equation (TVULE), a gain-adjustment neural network (GANN) is proposed, designed and analyzed. First, based on the exploited error monitoring function and neural dynamic method, a GANN ...

Recommender system uses user-item historical interactions to portray user preferences. Due to the problem of data sparseness, auxiliary information is introduced to describe user preferences, such as user/item attribute information. ...

Low-rank tensor completion (LRTC) has gained significant attention due to its powerful capability of recovering missing entries. However, it has to repeatedly calculate the time-consuming singular value decomposition (SVD). To address ...

This paper designs a novel online event-based near-optimal control scheme for multi-player nonzero-sum (NZS) games with partially unknown system dynamics. With the introduction of event-triggered mechanism (ETM), the repetitive ...

The outbreak and rapid spread of coronavirus disease 2019 (COVID-19) has had a huge impact on the lives and safety of people around the world. Chest CT is considered an effective tool for the diagnosis and follow-up of COVID-19. For ...

Continuous speech emotion recognition, which faces the problems of delay caused by annotators’ reaction time and noise caused by non-emotional segments, is a challenging subject in the field of affective computing. To solve these ...

Knowledge graph embedding, as the upstream task of link prediction which aims to predict new links between entities under the premise of known relations, its reliability greatly affects the performance of link prediction. However, ...

As a special type of neurodynamic methodology dedicated to finding zeros of equations, zeroing neurodynamics has shown a powerful ability in solving challenging online time-varying problems. Multi-linear systems, on the other hand, are ...

A state consensus cooperative adaptive dynamic programming (ADP) control strategy is proposed for a nonlinear multi-agent system (MAS) with output constraints. On the basis of the transformation function, state models of leader and ...

In this paper, we present a sparsity-aware deep network for automatic 3D/4D facial expression recognition (FER). We first propose a novel augmentation method to combat the data limitation problem for deep learning, specifically given ...

Recent studies have shown that biologically inspired Spiking Neural Networks (SNNs) has potentials for the mobile robot controls. Based on SNNs, an autonomous learning paradigm for controlling mobile robots is proposed in this work, ...

Motivated by mixture of probabilistic principal component analysis (PCA), which is time-consuming due to expectation maximization, this paper investigates a novel mixture of probabilistic PCA with clusterings for process monitoring. ...

A Reinforcement Learning (RL) agent interacts with the environment to learn a policy with high accumulated rewards through attempts and failures. However, RL suffers from its own trial-and-error learning nature, which results in an ...

For the multiple-input multiple-output (MIMO) downlink employing high-order quadrature amplitude modulation signaling and with nonlinear high power amplifiers (HPAs) at base station transmitter, the existing precoding designs relying ...

Detecting anomalies accurately in time series data has been receiving considerable attention due to its enormous potential for a wide array of applications. Numerous unsupervised anomaly detection methods for time series have been ...

This paper proposes a novel prescribed finite-time output feedback control scheme for quadrotor trajectory tracking control. The proposed control scheme considers the quadrotor modeling containing uncertain nonlinearities and strong ...

This paper focuses on the recognition problem of dynamical patterns consisting of sampling sequences. Specifically, based on the concept of structural stability, a novel similarity measure for dynamical patterns is first given. Then, a ...

This paper investigates the event-triggered synchronization of complex dynamic networks (CDNs) with semi-Markov switching and time-varying delay. First, by proposing auxiliary vectors with a few nonorthogonal polynomials, two slack-...

In the paper, data-driven finite-horizon robust formation-containment control scheme is developed based on integral reinforcement learning and zero-sum game for perturbed multi-agent networks with completely unknown nonlinear dynamics. ...

Face recognition systems are widely used for target recognition and identity authentication, such as automated teller machines, mobile phones, and entrance guard systems. However, face recognition systems are vulnerable to presentation ...

• Transform the max-bisection problem to a linearly constrained optimization problem.

The max-bisection problem has extensive applications in network engineering, making it imperative to develop effective methods to solve this problem. However, the efficient computation on this problem remains challenging due to its NP-...

Prognostics is the discipline of predicting the remaining useful life of a component or system in order to optimize the maintenance planning or the mission execution. Prognostics-enabled systems likely reduce the overall life-cycle ...

• We propose fuzzy reinforced polynomial neural networks based on PNN architecture.

In the field of dynamic system identification and prediction, linear models (e.g., autoregressive models), nonlinear models (namely, neural networks models), and hybrid predictors (HPs) that are a hybridization of linear and nonlinear ...

The structure information associated with message propagation has been proved to be effective to distinguish false and true rumors. However, existing methods lack an efficient way to learn the representation of the whole rumors which ...

In this paper, an adaptive neural network (NN) optimized control strategy is presented to improve the inherent tradeoff between ride comfort of passengers and the suspension travel for full vehicle active suspension system with state ...

Activation function is an important component of the convolutional neural network. Recently, nonlinear nonmonotonic activation functions such as Swish and Mish have illustrated good performance in deep learning structures. In this ...

The localization problem of unknown nodes in wireless sensor networks (WSN) has drawn increasing scholarly attention along together the popularity of meta-heuristic algorithms. To overcome the shortcomings of low accuracy that ...