Where ZK and ML intersect with Yi Sun and Daniel Kang
Zero Knowledge
Challenges in Integrating Zero Knowledge Proofs with Deep Learning
Integrating zero knowledge proofs with deep learning faces challenges due to the need to convert computations to integers or large cryptographically chosen primes, which are not close to differentiable operations like those in deep learning. Deep learning models rely on differentiability or discrete approximation, which poses a fundamental difficulty when reconciling the non-differentiable prime field object required for zero knowledge proofs with the differentiable operations used in deep learning.
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.
