Article
Computer Science, Artificial Intelligence
Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, Philip S. Yu
Summary: This survey provides a comprehensive review of knowledge graphs, covering topics such as knowledge graph representation learning, knowledge acquisition and completion, temporal knowledge graphs, and knowledge-aware applications. The study proposes a categorization and taxonomies on these topics, as well as explores emerging themes like metarelational learning, commonsense reasoning, and temporal knowledge graphs. Additionally, the research offers curated data sets and open-source libraries to facilitate future research in the field of knowledge graphs.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zewen Li, Fan Liu, Wenjie Yang, Shouheng Peng, Jun Zhou
Summary: This review provides insights into the development history of CNN, a overview of various convolutions, introduction to classic and advanced CNN models, conclusions drawn from experimental analysis, rules of thumb for function and hyperparameter selection, and applications of 1-D, 2-D, and multidimensional convolutions. Moreover, it also discusses open issues and promising directions for CNN as guidelines for future work.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola
Summary: The research presents a multi-branch architecture to improve representation learning in convolutional neural networks, leading to enhanced performance of deep learning models. Their approach leverages channel-wise attention to combine the strengths of feature-map attention and multi-path representation, resulting in more diverse representations.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)
Article
Computer Science, Artificial Intelligence
Yongming Li, Yanjun Liu, Shaocheng Tong
Summary: This article presents an adaptive neural network output feedback optimized control design for strict-feedback nonlinear systems with unknown internal dynamics. By constructing optimal cost functions for subsystems and using the actor-critic architecture, virtual and actual optimal controllers are developed to ensure the boundedness of all closed-loop signals. The proposed strategy also guarantees that system states are always confined within some preselected compact sets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Review
Computer Science, Theory & Methods
Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, Jianfeng Gao
Summary: This article provides a comprehensive review of over 150 deep learning-based models for text classification developed in recent years. It discusses their technical contributions, similarities, and strengths, as well as summarizes popular datasets used for text classification. The article also includes a quantitative analysis of the performance of different deep learning models on popular benchmarks and discusses future research directions.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Theory & Methods
Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, Mubarak Shah
Summary: Transformer models have shown impressive results in computer vision tasks by simulating long dependencies, supporting parallel processing, and handling multi-modal data. They are widely used in visual recognition, generative modeling, multi-modal tasks, video processing, low-level vision, and three-dimensional analysis, showcasing their strengths in scalability and flexibility.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Theory & Methods
Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
Summary: Researchers have shown relatively lower interest in active learning compared to deep learning, but with the increasing demand for large-scale high-quality annotated datasets, active learning is receiving more attention. This article provides a comprehensive survey on deep active learning, including a formal classification method, an overview of existing work, and an analysis of developments from an application perspective.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Artificial Intelligence
Ravid Shwartz-Ziv, Amitai Armon
Summary: The study compares the performance of deep learning models and XGBoost on various datasets, finding that XGBoost outperforms deep models and requires less tuning. However, an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.
INFORMATION FUSION
(2022)
Article
Computer Science, Hardware & Architecture
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng
Summary: This method achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. The algorithm represents a scene using a fully connected deep network and synthesizes views by querying 5D coordinates and using volume rendering techniques.
COMMUNICATIONS OF THE ACM
(2022)
Proceedings Paper
Computer Science, Information Systems
Peiyuan Jiang, Daji Ergu, Fangyao Liu, Ying Cai, Bo Ma
Summary: This paper provides a brief overview of the YOLO algorithm and its subsequent advanced versions, highlighting the ongoing improvement of the algorithm. The analysis reveals the differences and similarities among different YOLO versions and between YOLO and CNNs.
8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT (ITQM 2020 & 2021): DEVELOPING GLOBAL DIGITAL ECONOMY AFTER COVID-19
(2022)
Article
Computer Science, Artificial Intelligence
Zhifei Li, Hai Liu, Zhaoli Zhang, Tingting Liu, Neal N. Xiong
Summary: This article proposes a novel heterogeneous GNNs framework based on attention mechanism to address the aggregation of complex graph data containing various types of entities and relations in KGs. By learning weight values to aggregate features from different relation-paths for embedding representation, it captures various types of semantic information and selectively aggregates informative features.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Review
Computer Science, Theory & Methods
Ane Blazquez-Garcia, Angel Conde, Usue Mori, Jose A. Lozano
Summary: Recent technological advancements have enabled the collection of large amounts of data over time, leading to the generation of time series. Mining this data for outliers has become an important task for researchers and practitioners. This review aims to provide a structured and comprehensive overview of unsupervised outlier detection techniques in the context of time series, presenting a taxonomy based on key aspects characterizing outlier detection methods.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Artificial Intelligence
Guang Yang, Qinghao Ye, Jun Xia
Summary: XAI is an emerging research field in machine learning that aims to explain the decision-making process of AI systems. In healthcare, XAI is becoming increasingly important for improving the transparency and explainability of deep learning applications, although the lack of explainability in most AI systems may be a major barrier to successful implementation of AI tools in clinical practice.
INFORMATION FUSION
(2022)
Article
Computer Science, Artificial Intelligence
Hao Shen, Xiaohui Hu, Jing Wang, Jinde Cao, Wenhua Qian
Summary: This work explores the $H_{infinity }$ synchronization issue for singularly perturbed coupled neural networks (SPCNNs) affected by both nonlinear constraints and gain uncertainties. A novel double-layer switching regulation containing Markov chain and persistent dwell-time switching regulation (PDTSR) is proposed to design a mode-dependent synchronization controller for the network. New sufficient conditions are established to ensure the mean-square exponential stability of the synchronization error systems with the specified level of the $H_{infinity }$ performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Xiaorui Zhang, Wenfang Zhang, Wei Sun, Xingming Sun, Sunil Kumar Jha
Summary: In this paper, a 3D medical watermarking algorithm based on wavelet transform is proposed, which utilizes PCA transform to reduce data dimension and a BF-PSO model to find the optimal embedding parameters, achieving the optimal balance between embedding capacity and imperceptibility. Experimental results based on a standard MRI brain volume dataset in MATLAB software show that the proposed algorithm has strong robustness and minimal deformation of the 3D model after watermark embedding.
COMPUTER SYSTEMS SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Theory & Methods
Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui
Summary: This article provides a comprehensive review of recent research efforts on GNN-based recommender systems. It includes a taxonomy of GNN-based recommendation models, analysis of challenges in applying GNN on different data types, and discussion of future perspectives in this field.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Sen Qiu, Hongkai Zhao, Nan Jiang, Zhelong Wang, Long Liu, Yi An, Hongyu Zhao, Xin Miao, Ruichen Liu, Giancarlo Fortino
Summary: This paper introduces common wearable sensors, smart wearable devices, and key application areas, proposing fusion methods for multi-modality and multi-location sensors. It comprehensively surveys important aspects of wearable sensor fusion methods in human activity recognition, including new technologies in unsupervised learning and transfer learning, while also discussing open research issues that need further investigation and improvement.
INFORMATION FUSION
(2022)
Article
Computer Science, Artificial Intelligence
Hwanjun Song, Minseok Kim, Dongmin Park, Yooju Shin, Jae-Gil Lee
Summary: The lack of high-quality labels in real-world scenarios is a concern in deep learning. This survey provides a comprehensive review of robust training methods and compares their superiority. It also analyzes noise rate estimation and evaluation methodology.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yan-Jun Liu, Wei Zhao, Lei Liu, Dapeng Li, Shaocheng Tong, C. L. Philip Chen
Summary: This article investigates the problem of tracking control for a class of nonlinear time-varying full state constrained systems. The intelligent controller and adaptive law are developed by constructing the time-varying asymmetric barrier Lyapunov function (BLF) and combining it with the backstepping algorithm. Neural networks (NNs) are used to approximate the uncertain function. This article considers constraint boundaries that are both related to state and time, making the design of the control algorithm more complex and difficult. The effectiveness of the control algorithm is verified through numerical simulation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Review
Computer Science, Artificial Intelligence
Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer
Summary: This article reviews the latest single-source deep unsupervised domain adaptation (DA) methods for visual tasks and discusses new perspectives for future research. The article starts with the definitions of different DA strategies and descriptions of existing benchmark datasets, then summarizes and compares different categories of methods, and finally discusses future research directions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
