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
On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease
Raghav Singhal, Mukund Sudarshan, Anish Mahishi, Sri Kaushik, Luke Ginocchio, Angela Tong, Hersh Chandarana, Daniel K. Sodickson, Rajesh Ranganath, Sumit Chopra
Feasibility and Transferability of Transfer Learning: A Mathematical Framework
Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum