Data-Centric Approach to Machine Learning in Health Applications
Explore the critical importance of robust data management practices in machine learning and AI for health applications in this insightful talk by Carl Kesselman, Director of ISI's Informatics Systems Research division. Delve into the challenges faced in experimental procedures and the consequences of poor data handling, which often lead to weakened or incorrect algorithms. Examine the shift from algorithm-centric to data-centric approaches in solving complex problems. Discover the range of concerns in establishing sound data practices for machine learning experiments, illustrated with specific examples from datasets used in the Center for AI Research In Medicine. Gain valuable insights into practical solutions and their applications in Neuroscience and cell biology, as presented by Kesselman, who is also co-Director of the Center for Research in AI in Medicine.