OOIR: Observatory of International Research

Papers

(The H4-Index of Neural Networks is 49. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-02-01 to 2025-02-01.)

Article	Citations
Computational reproductions of external force field adaption without assuming desired trajectories	282
Self-supervised Learning for DNA sequences with circular dilated convolutional networks	219
Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach	216
CreINNS: Credal-Set Interval neural networks for uncertainty estimation in classification tasks	210
Analysis of medical images super-resolution via a wavelet pyramid recursive neural network constrained by wavelet energy entropy	203
GeneWorker: An end-to-end robotic reinforcement learning approach with collaborative generator and worker networks	179
A novel fractional-order memristive Hopfield neural network for traveling salesman problem and its FPGA implementation	122
Progressive Neighbor-masked Contrastive Learning for Fusion-style Deep Multi-view Clustering	113
Early stopping by correlating online indicators in neural networks	112
Multi-view subspace clustering via adaptive graph learning and late fusion alignment	110
FastGAE: Scalable graph autoencoders with stochastic subgraph decoding	108
Multi-view Teacher–Student Network	105
On the Kolmogorov neural networks	101
Towards global neural network abstractions with locally-exact reconstruction	93
Adaptive neural network asymptotic tracking control for nonstrict feedback stochastic nonlinear systems	92
Filter pruning for convolutional neural networks in semantic image segmentation	86
Spatial reconstructed local attention Res2Net with F0 subband for fake speech detection	82
Finite-time cluster synchronization for complex dynamical networks under FDI attack: A periodic control approach	80
Structure enhanced deep clustering network via a weighted neighbourhood auto-encoder	80
CURRENT EVENTS	73
Editorial Board	73
Evolved explainable classifications for lymph node metastases	70
Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization	70
MV-SHIF: Multi-view symmetric hypothesis inference fusion network for emotion-cause pair extraction in documents	68
Expressive power of ReLU and step networks under floating-point operations	68

Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world	67
vEpiNet: A multimodal interictal epileptiform discharge detection method based on video and electroencephalogram data	67
Neural Q-learning for discrete-time nonlinear zero-sum games with adjustable convergence rate	66
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule	64
A lightweight and gradient-stable neural layer	64
Boosting adversarial robustness via self-paced adversarial training	61
Announcement of the Neural Networks Best Paper Award	61
Using top-down modulation to optimally balance shared versus separated task representations	60
Spiking generative adversarial network with attention scoring decoding	60
Towards efficient network compression via Few-Shot Slimming	59
Smoothing inertial neurodynamic approach for sparse signal reconstruction via	59
Neural feedback facilitates rough-to-fine information retrieval	57
Adams-based hierarchical features fusion network for image dehazing	57
Using source data to aid and build variational state–space autoencoders with sparse target data for process monitoring	55
A surge of submissions	55
Efficient spiking neural network design via neural architecture search	54
Noncompact uniform universal approximation	51
Advanced optimal tracking integrating a neural critic technique for asymmetric constrained zero-sum games	51
Graph-based social relation inference with multi-level conditional attention	51
Data-driven learning of chaotic dynamical systems using Discrete-Temporal Sobolev Networks	51
Structure enhanced prototypical alignment for unsupervised cross-domain node classification	50
Memristor-based spiking neural network with online reinforcement learning	49
WDMNet: Modeling diverse variations of regional wind speed for multi-step predictions	49
Adversarial Lagrangian integrated contrastive embedding for limited size datasets	49