A General Debiasing Framework with Counterfactual Reasoning for Multimodal Public Speaking Anxiety Detection

Information Science, Computer Science, Artificial Intelligence,
public speaking anxiety detection   multimodal debiasing   spurious correlation   counterfactual reasoning   dataset  

Academic Background and Problem Introduction In the field of education today, Public Speaking Anxiety (PSA) is a widespread phenomenon, especially among non-native language learners. This anxiety not only affects learners’ ability to express themselves but may also hinder their personal development. To help learners overcome this issue, researchers...

Rehearsal-Based Continual Learning with Dual Prompts

Information Science, Computer Science, Artificial Intelligence,
Continual Learning   Dual Prompts   Knowledge Distillation   Catastrophic Forgetting   Neural Networks  

Academic Background In the fields of machine learning and neural networks, continual learning is an important research direction. The goal of continual learning is to enable models to continuously learn new knowledge across a series of tasks while avoiding forgetting previously acquired knowledge. However, existing continual learning methods face a...

Complex Quantized Minimum Error Entropy with Fiducial Points: Theory and Application in Model Regression

Information Science, Electronic Information, Computer Science, Artificial Intelligence,
fixed-point algorithm   quantized technique   regression analysis   linear-in-parameters model   convergence   complex domain  

Theory and Application of Complex Quantized Minimum Error Entropy with Fiducial Points: Breakthroughs in Model Regression Academic Background In the fields of machine learning and signal processing, the presence of non-Gaussian noise often adversely affects model performance. Although the traditional Mean Squared Error (MSE) is theoretically and co...

DRTN: Dual Relation Transformer Network with Feature Erasure and Contrastive Learning for Multi-Label Image Classification

Information Science, Computer Science, Artificial Intelligence,
Multi-label image classification   Transformer   Pseudo-region   Feature erasure   Contrastive learning  

New Breakthrough in Multi-Label Image Classification: Dual Relation Transformer Network Academic Background Multi-Label Image Classification (MLIC) is a fundamental yet highly challenging problem in the field of computer vision. Unlike single-label image classification, MLIC aims to assign multiple labels to objects within a single image. Due to th...

ADAMT: Adaptive Distributed Multi-Task Learning for Efficient Image Recognition in Mobile Ad-Hoc Networks

Information Science, Computer Science, Artificial Intelligence,
Mobile Ad-Hoc Networks   Distributed Multi-Task Learning   Image Recognition   Decentralized Learning   Resource Optimization  

Adaptive Distributed Multi-Task Learning Framework ADAMT: Efficient Image Recognition in Mobile Ad-hoc Networks Academic Background Distributed machine learning in Mobile Ad-hoc Networks (MANETs) faces significant challenges. These challenges primarily stem from the limited computational resources of devices, non-independent and identically distrib...

Episodic Memory-Double Actor–Critic Twin Delayed Deep Deterministic Policy Gradient

Information Science, Computer Science, Artificial Intelligence,
deep reinforcement learning   sample efficiency   actor–critic algorithm   episodic memory   continuous control tasks  

Academic Background Deep Reinforcement Learning (DRL) has achieved remarkable success in various fields such as gaming, robotics, navigation, computer vision, and finance. However, existing DRL algorithms generally suffer from low sample efficiency, requiring vast amounts of data and training steps to achieve desired performance. Particularly in co...