Audio Edition: How Distillation Makes AI Models Smaller and Cheaper
About this episode
The episode discusses how distillation allows researchers to train smaller and cheaper AI models using larger teacher models.
Fundamental technique lets researchers use a big, expensive “teacher” model to train a “student” model for less. The story How Distillation Makes AI Models Smaller and Cheaper first appeared on Quanta Magazine.
Topics covered
- AI
- distillation
- machine learning
- model training
- cost reduction
More episodes of The Quanta Podcast
- Audio Edition: Astrophysicists Find No ‘Hair’ on Black Holes
- The AI Revolution in Math Has Arrived
- Ice Is Way More Complex Than It Seems
- Our Immune Systems Are Full of Ancient Weapons
Explore listener stats, chart rankings, contacts and more on the The Quanta Podcast podcast page.