Task Feasibility
Task feasibility research assesses whether a given task is achievable within the constraints of a system, focusing on identifying limitations and developing strategies for success. Current investigations explore this across diverse domains, including machine unlearning, AI-driven attacks, autonomous programming, and medical image analysis, employing techniques like large language models, neural networks, and optimization algorithms to evaluate performance and identify bottlenecks. These studies are crucial for advancing the responsible development and deployment of AI systems and for optimizing resource allocation in various scientific and engineering applications. The ultimate goal is to improve the reliability and efficiency of complex systems by understanding and addressing inherent limitations.
Papers
Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities
Felix Wagner, Wentian Xu, Pramit Saha, Ziyun Liang, Daniel Whitehouse, David Menon, Virginia Newcombe, Natalie Voets, J. Alison Noble, Konstantinos Kamnitsas
On the Feasibility of Fidelity$^-$ for Graph Pruning
Yong-Min Shin, Won-Yong Shin