Episode 18: Research Data Science in Biotech
Vanishing Gradients
00:00
The Current State and Challenges of Bayesian Inference
Exploring the current adoption and challenges of Bayesian inference, including the need to overcome human laziness and the difficulty of incorporating statistical skills into education. The chapter also dives into the problem of making data say anything with the right priors and the lack of good tooling for sensitivity analysis of Bayesian models. Touching on the philosophical and domain-specific nature of determining reasonable priors and sensitivity analysis, the chapter concludes with a teaser for a future episode on Bayesian inference.
Transcript
Play full episode
