main concepts scientists sections

Zihan Wang

1 articles · 5 co-authors · latest: 2026-01-11
2,168 citations · h-index 11 · 31 papersNorthwestern UniversityData: Semantic Scholar
Min Chen · Canyu Chen · Zeguan Wu · Manling Li · Junyu Liu

We have retold 1 papers by this author. most often about: von Neumann entropy, Explainable AI, entropy. 5 co-authors across our retellings.

active learning · ai self correction · ai speech analysis · feature importance · Large Language Models · learning rate · neural network regression · parameter · parameter fitting · pattern recognition · protein language model · quantum entanglement training · regularization methods · Reinforcement Learning · speech recognition · training · transformers · Weakly Supervised Learning · von Neumann entropy · Explainable AI
second law of thermodynamics · Bekenstein-Hawking entropy · Boltzmann distribution · first law of thermodynamics · AdS/CFT correspondence · holographic principle · fluctuation-dissipation theorem · law of conservation of energy · zeroth law of thermodynamics · third law of thermodynamics · Holevo bound · Landauer's principle · Lindblad equation · Carnot's theorem · Hawking area theorem · Fokker–Planck equation · Boltzmann equation · equipartition theorem · principle of maximum entropy · ergodic theorem
Links in the knowledge graph
Machine Learning2026-01-111 minarXiv:2601.06788express
Why neural networks are like black holes: a lesson from 'bald' models
Fine-tuning a neural network is like trying to alter a black hole without touching its event horizon: you change only a tiny fraction of parameters. Researchers looked inside and saw stunning patterns — strong links between pieces of the model, akin to quantum entanglement.
Min Chen·Zihan Wang·Canyu Chen·Zeguan Wu·Manling Li·Junyu Liu
Bekenstein-Hawking entropyJacob BekensteinStephen HawkingDavid Deutschvon Neumann entropyExplainable AIentropy
SimplePopularAdvanced