Zero-Shot Learning
Discover the innovative approaches to training models without extensive labeled data. Kate discusses the effectiveness of large-scale models like CLIP and how prompting can enable them to recognize new categories with minimal or no training data. This method not only enhances performance but also addresses the challenges of data collection and labeling in real-world applications.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
More Language, Less Labeling with Kate Saenko - #580
Related Questions
Is less labeled data needed for training machine learning models as discussed in the episodes Machine Learning on Images with Noisy Human-centric Labels and Unlocking Raw Data Sets?
Is less labeled data needed for training machine learning models in the episode Daniel Situnayake: AI on the Edge and the clip Training without Labels?
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?