Measuring Task Difficulty
Rosanne discusses the concept of intrinsic dimension and its significance in measuring the difficulty of machine learning tasks in relation to different networks. She shares insights from her early research experiences and highlights how their work has influenced later methods like low rank adaptation. The conversation delves into the complexities of quantifying task difficulty by combining datasets with network architectures, illustrating how performance can vary dramatically based on these combinations.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
797: Deep Learning Classics and Trends — with Dr. Rosanne Liu
Related Questions