Where ZK and ML intersect with Yi Sun and Daniel Kang
Zero Knowledge
00:00
Is There a Wiggle Room in Machine Learning?
The core premise of machine learning is that your model should be differentiable. To generate a zero knowledge proof, you have to somehow transform your computation to one where every variable is an integer or modulo. There's some challenge to doing that. But then I always think about the fact that like NVIDIA moved everything to 8-bit and you know like it's not really as smooth as you think it is.
Transcript
Play full episode
