[14] Been Kim - Interactive and Interpretable Machine Learning Models
The Thesis Review
00:00
The Future of Machine Learning
In the world of machine learning, right now we have models that are mostly uninterpretable. Pope's stock method is there to help them to kind of in this transition area era for it to be used responsibly. But perhaps at some point in 10 years or more, these models are used then used to too many areas in life and to be affecting too many people’s lives. So let's just slowly switching to completely inherently interpret a model. That is possible. Now, do I think that that will happen within my lifetime? I don't know. We've seen transformer models or GPTs, three and other complex models that or architecture search that's another good example of having
Play episode from 37:32
Transcript
