Telescopic broad Bayesian learning for big data stream
In this paper, a novel telescopic broad Bayesian learning (TBBL) is proposed for sequential
learning. Conventional broad learning suffers from the singularity problem induced by the …
learning. Conventional broad learning suffers from the singularity problem induced by the …
Self-supervised EEG representation learning with contrastive predictive coding for post-stroke patients
F Xu, Y Yan, J Zhu, X Chen, L Gao, Y Liu… - … Journal of Neural …, 2023 - World Scientific
Stroke patients are prone to fatigue during the EEG acquisition procedure, and experiments
have high requirements on cognition and physical limitations of subjects. Therefore, how to …
have high requirements on cognition and physical limitations of subjects. Therefore, how to …
Enhancing zero-shot object detection with external knowledge-guided robust contrast learning
Zero-shot object detection aims to identify objects from unseen categories not present during
training. Existing methods rely on category labels to create pseudo-features for unseen …
training. Existing methods rely on category labels to create pseudo-features for unseen …
A Bidirectional Feedforward Neural Network Architecture Using the Discretized Neural Memory Ordinary Differential Equation.
Deep Feedforward Neural Networks (FNNs) with skip connections have revolutionized
various image recognition tasks. In this paper, we propose a novel architecture called …
various image recognition tasks. In this paper, we propose a novel architecture called …
A hybrid online off-policy reinforcement learning agent framework supported by transformers
EA Villarrubia-Martin, L Rodriguez-Benitez… - … Journal of Neural …, 2023 - World Scientific
Reinforcement learning (RL) is a powerful technique that allows agents to learn optimal
decision-making policies through interactions with an environment. However, traditional RL …
decision-making policies through interactions with an environment. However, traditional RL …
Text-driven online action detection
<? show [AQ ID= GQ2 POS=-24pt]?><? show [AQ ID= GQ5 POS= 12pt]?> Detecting actions
as they occur is essential for applications like video surveillance, autonomous driving, and …
as they occur is essential for applications like video surveillance, autonomous driving, and …
Multi-Label Zero-Shot Learning Via Contrastive Label-Based Attention
S Meng, R Jiang, X Tian, F Zhou… - … journal of neural …, 2025 - pubmed.ncbi.nlm.nih.gov
Multi-label zero-shot learning (ML-ZSL) strives to recognize all objects in an image,
regardless of whether they are present in the training data. Recent methods incorporate an …
regardless of whether they are present in the training data. Recent methods incorporate an …