Rethinking Model Size: Train Large, Then Compress with Joseph Gonzalez - #378
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Enhancing Interpretability in Machine Learning
This chapter explores the complexities of explainability in machine learning, particularly in deep learning systems, and discusses the integration of decision trees to improve interpretability. It highlights the distinction between explanations and interpretability, emphasizing the importance of linking model decisions back to data for corrections and better understanding.
Transcript
Play full episode
