The Problem with Black Boxes with Cynthia Rudin - TWIML Talk #290
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Deep Learning and Interpretability in AI
This chapter explores the application of deep learning to tabular data, emphasizing its effectiveness in machine learning competitions such as Kaggle. It also delves into the challenge of creating interpretable neural networks that can articulate their reasoning, using examples from computer vision and bird identification datasets to highlight the importance of transparency in model predictions.
Transcript
Play full episode
