Explainability, Reasoning, Priors and GPT-3
Machine Learning Street Talk (MLST)
Understanding Explainability in Machine Learning
This chapter explores the critical role of trustworthy explanations in machine learning, particularly in credit applications within the banking sector. It discusses various model types, from traditional methods like logistic regression to advanced techniques such as LIME, and emphasizes the trade-off between predictability and explainability. Additionally, the chapter evaluates neural network competence, activation functions, and the challenges of current image recognition technologies.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
