ZeroShotKnowledgeTransfer
ZeroShotKnowledgeTransfer copied to clipboard
polo5
Accompanying code for the paper "Zero-shot Knowledge Transfer via Adversarial Belief Matching"
Results
1
ZeroShotKnowledgeTransfer issues
Sort by
recently updated
recently updated
newest added
Using random input yields even higher accuracy (95.77901%) and faster convergence in toy experiment😄 Of course it's not the same in higher dimensions, but I'm just going to mention this...
