Alexander Scheinker

1 articles · 0 co-authors · latest: 2026-08-01
53 citations · h-index 5 · 27 papersData: Semantic Scholar

We have retold 1 papers by this author. most often about: Contrastive Learning, self-supervised learning, nonlinear dynamics.

Links in the knowledge graph
Statistical ML2026-08-012 minarXiv:2608.00675express
Round Trip: How a Neural Network Checks Itself Without Hints
A neural network predicts the future of a system — say, how plasma will swirl in a magnetic field or how a face in a video will change. Errors are inevitable, and the further it looks ahead, the more they accumulate. Checking against the correct answer during operation is impossible: it simply doesn't exist.