External Influence
External influence, encompassing how various factors impact systems and processes, is a burgeoning research area with applications across diverse fields. Current studies focus on quantifying and mitigating the influence of biases in large language models, noise in image processing, and user preferences in recommender systems, often employing techniques like deep learning, Gaussian filtering, and stochastic simulation. Understanding and controlling external influences is crucial for developing robust, fair, and reliable AI systems and improving the accuracy and efficiency of various technologies, from medical image analysis to autonomous vehicles.
Papers
Influence of image noise on crack detection performance of deep convolutional neural networks
Riccardo Chianese, Andy Nguyen, Vahidreza Gharehbaghi, Thiru Aravinthan, Mohammad Noori
Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets
Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh