AT‐AER: Adversarial Training With Adaptive Example Reuse
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Adversarial training (AT) is widely regarded as a crucial defense method for deep neural networks against adversarial attacks. Most of the existing AT methods suffer from the problems of insufficient coverage of perturbation space and robust overfitting.
Meng Hu +5 more
wiley +1 more source
Dynamic optimization and coordination of the new energy vehicle supply chain based on credit trading and green innovation. [PDF]
Sci RepZhao L, Li J, Bao X.
europepmc +1 more source
Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Policy heterogeneity is crucial for achieving sophisticated coordination in complex collaborative tasks, which has emerged as one of the key challenges in multi‐agent reinforcement learning (MARL) in recent years. Notably, the grouping paradigm has made remarkable progress in addressing policy heterogeneity.
Yirui Liu +6 more
wiley +1 more source
Differential shooting training in youth basketball players: an analysis of performance effects. [PDF]
Front PsycholBurkaitė G +4 more
europepmc +1 more source
From Ambiguous Queries to Verifiable Insights: A Task‐Driven Framework for LLM‐Powered SOC Analysis⋆
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Security operations centre (SOC) analysts must investigate alerts, correlate threat intelligence and interpret heterogeneous telemetry under tight timing constraints. Although large language models (LLMs) offer strong understanding capabilities, directly applying them to SOC environments remains challenging due to semantic ambiguity in analyst
Huan Zhang +5 more
wiley +1 more source
Research on Joint Game-Theoretic Modeling of Network Attack and Defense Under Incomplete Information. [PDF]
Entropy (Basel)Wang Y, Liu X, Yu X.
europepmc +1 more source
High Voltage, EarlyView.ABSTRACT The emergence of (ultra)wide bandgap ((U)WBG)‐based devices has significantly enhanced performance in high‐frequency switching applications, enabling breakthroughs in electric transportation, aerospace, and renewable energy systems. However, it also presents considerable challenges to insulation systems, such as electric motor winding ...
Easir Arafat +3 more
wiley +1 more source
Effect of Contextual Interference and Differential Learning on Motor Skill Development and Motivation in Novice Basketball Players. [PDF]
Eur J Sport SciShamshiri G, Fazeli D, Nazemzadegan G.
europepmc +1 more source
A sport inspired kabaddi game optimizer for accurate parameter estimation of solar photovoltaic models. [PDF]
Sci RepAyyarao TSLV +3 more
europepmc +1 more source
Australian Journal of Agricultural and Resource Economics, EarlyView.ABSTRACT This study examines the factors influencing producer adoption of cover cropping and no‐till farming, two key carbon sequestration practices, within the context of voluntary carbon credit programmes (CCPs) in Kansas. Using a mixed‐methods survey that combines discrete choice experiments with farm‐level data from 370 producers, we estimate ...
Grant Edward Gardner +2 more
wiley +1 more source