Data Efficiency Insights
Jeremy emphasizes that organizations often overestimate the amount of data needed for effective machine learning, highlighting the power of transfer learning to achieve state-of-the-art results with minimal data. He discusses the challenges of recommender systems, particularly the cold start problem, and questions the trade-off between user privacy and the benefits of data sharing for personalization.In this clip
From this podcast
Lex Fridman Podcast
Jeremy Howard: fast.ai Deep Learning Courses and Research | Lex Fridman Podcast #35
Related Questions
Is less labeled data needed for training machine learning models as discussed in the episode "Big Data Doesn't Exist" and the clip "Deep Learning Insights" featuring Ilya Sutskever (OpenAI Chief Scientist) - Building AGI, Alignment, Spies, Microsoft, & Enlightenment and Running Out of Reasoning Tokens?
Is less labeled data needed for training machine learning models as discussed in the episode Cognilytica and the clip Future of Data featuring Ilya Sutskever (OpenAI Chief Scientist) in the episode "Big Data Doesn't Exist" and the clip "Deep Learning Insights" - Building AGI, Alignment, Spies, Microsoft, & Enlightenment and Running Out of Reasoning Tokens?
Is less labeled data needed for training machine learning models as discussed in the episode Big Data Doesn't Exist and the clip Deep Learning Insights featuring Ilya Sutskever (OpenAI Chief Scientist) - Building AGI, Alignment, Spies, Microsoft, & Enlightenment and Running Out of Reasoning Tokens?