Showing papers in "Neurocomputing in 2020"

TL;DR: This survey paper will help industrial users, data analysts, and researchers to better develop machine learning models by identifying the proper hyper-parameter configurations effectively and introducing several state-of-the-art optimization techniques.

TL;DR: A brief introduction of SVMs is provided, many applications are described and challenges and trends are summarized, especially in the some fields.

TL;DR: A comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.

TL;DR: A comprehensive survey of recent advances in visual object detection with deep learning can be found in this article, where the authors systematically analyze the existing object detection frameworks and organize the survey into three major parts: detection components, learning strategies, and applications and benchmarks.

TL;DR: This work attempts to review and summarize the development of the Convolutional Network based Fault Diagnosis (CNFD) approaches comprehensively, and points out the characteristics of current development, facing challenges and future trends.

TL;DR: A novel temporal attention encoder–decoder model that integrates the traditional encode context vector and temporal attention vector for jointly temporal representation learning is proposed, based on bi-directional long short-term memory networks (Bi-LSTM) layers.

TL;DR: A brief review of research efforts on deep-learning-based semantic segmentation methods is provided, which categorize the related research according to its supervision level, i.e., fully-supervised methods, weakly- supervised methods and semi-super supervised methods.

TL;DR: An integrated algorithm which combines adaptive unscented kalman filter (AUKF) and genetic algorithm optimized support vector regression (GA-SVR) achieves better prediction accuracy than existed methods.

TL;DR: In this paper, a probabilistic forecasting framework based on convolutional neural network (CNN) for multiple related time series forecasting is presented, which can be applied to estimate probability density under both parametric and non-parametric settings.

TL;DR: This paper reviews the research progress of the deep transfer learning for the machinery fault diagnosis in recently years, summarizing, classifying and explaining many publications on this topic with discussing various deep transfer architectures and related theories.

TL;DR: Shabbeersh et al. as mentioned in this paper tried to find the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets, and performed experiments with four CNN architectures having different depths.

TL;DR: This work introduces the theory of attention in psychology to image caption generation with a combination of convolutional neural network over images and long-short term memory network over sentences.

TL;DR: Experimental results demonstrate the effectiveness and superiority of RCNN in improving the accuracy and convergence of RUL prediction, and more importantly, RCNN is able to provide a probabilistic RUL Prediction result, which breaks the inherent limitation of CNNs and facilitates maintenance decision making.

TL;DR: A comprehensive literature review of U-shaped networks applied to medical image segmentation tasks, focusing on the architectures, extended mechanisms and application areas in these studies.

TL;DR: Experimental results on three small and medium basins in China suggest that the proposed STA-LSTM model outperforms Historical Average, Fully Connected Network (FCN), Convolutional Neural Networks (CNN), Graphconvolutional Networks (GCN), original LSTM, spatial attention LSTm, and temporal attention L STM (TA-L STM) in most cases.

TL;DR: Zhang et al. as mentioned in this paper proposed a pose guided structured region ensemble network (Pose-REN), which extracts regions from the feature maps of convolutional neural network and generates more optimal and representative features for hand pose estimation.

TL;DR: A novel end-to-end network with attention mechanism for automatic facial expression recognition is proposed and LBP features and attention mechanism are combined to enhance the attention model to obtain better results.

TL;DR: In this article, a probabilistic model of the objective is used to compute an acquisition function that estimates the expected utility (for solving the optimization problem) of evaluating the objective at each potential new point.

TL;DR: In this paper, a novel Wasserstein distance-based deep transfer learning (WD-DTL) network was proposed for both supervised and unsupervised fault diagnosis tasks. But, the proposed network is not suitable for the task of automatic fault diagnosis.

TL;DR: Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based data augmentation approaches are researched to generate data samples to supplement low-data input set in fault diagnosis field and help improve the fault diagnosis accuracies.

TL;DR: Comparative experimental results show that the designed statistical analysis and AE based IDS achieves better classification performance compared to conventional deep and shallow machine learning and other recently proposed state-of-the-art techniques.

TL;DR: A bidirectional LSTM model with self-attention mechanism and multi-channel features (SAMF-BiLSTM) that can fully exploit the relationship between target words and sentiment polarity words in a sentence, and does not rely on manually organized sentiment lexicon is proposed.

TL;DR: The work was funded by The Leverhulme Trust Research Project Grant RPG-2016-252 entitled “Novel Approaches for Constructing Optimised Multimodal Data Spaces”.

TL;DR: A novel time series forecasting model, named SeriesNet, which can fully learn features of time series data in different interval lengths is presented, which has higher forecasting accuracy and has greater stableness on several typical time series datasets.

TL;DR: With this method, the generated visual maps can be easily interpreted by an ophthalmologist in order to find the underlying statistical regularities that help to the diagnosis of this eye disease.

TL;DR: Experimental results performed on the Center for Advanced Studies in Adaptive Systems datasets show that the proposed LSTM-based approaches outperform existing DL and ML methods, giving superior results compared to the existing literature.

TL;DR: A novel memory interconnection Lyapunov–Krasovskii functional is structured by taking full advantage of more information of sampling interval and state, and developing some new terms to investigate the finite-time (FT) H∞ synchronization issue for complex networks with stochastic cyber attacks and random memory information exchanges.

TL;DR: A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence.

TL;DR: A novel deep convolutional neural network which combines symmetry have been proposed to automatically segment brain tumors, called Deep Convolutional Symmetric Neural Network (DCSNN), extends DCNN based segmentation networks by adding symmetric masks in several layers.

TL;DR: A neural fuzzy-based model predictive tracking scheme (NFMPC) for reliable tracking control is proposed to the developed four wheel-legged robot, and the fuzzy neural network approximation is applied to estimate the unknown physical interaction and external dynamics of the robot system.