main concepts scientists sections

Erik G. Larsson

1 articles · 2 co-authors · latest: 2026-07-14
40 citations · h-index 3 · 15 papersData: Semantic Scholar
Chung-Hsuan Hu · Zheng Chen

We have retold 1 papers by this author. most often about: self-supervised learning, Reinforcement Learning, Recurrent Neural Networks. 2 co-authors across our retellings.

boosted decision tree · Contrastive Learning · digital twin training · labeled data · multifractal detrended fluctuation analysis · protein language model · training · training data · transfer learning · self-supervised learning · Reinforcement Learning · Recurrent Neural Networks · Weakly Supervised Learning · entropy
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 · Landauer's principle · Lindblad equation · Carnot's theorem · Hawking area theorem · Fokker–Planck equation · Boltzmann equation · equipartition theorem · principle of maximum entropy · ergodic theorem · Liouville's theorem
Links in the knowledge graph
Information Theory2026-07-141 minarXiv:2607.13119express
Dual Hints: How Smartphones Learn Without Glitches
When you type 'salad' and the keyboard suggests 'Caesar,' behind the scenes millions of phones are jointly learning to predict words. They share not your messages, but only improvements to the common algorithm, like a coach who sends athletes only the tweaks to the plan: 'add 5 push-ups to yesterday’s routine.' Information entropy helps send only unexpected, valuable updates.
Chung-Hsuan Hu·Zheng Chen·Erik G. Larsson
Rainer WeissKip ThorneBarry Barishself-supervised learningReinforcement LearningRecurrent Neural NetworksWeakly Supervised Learningentropy
SimplePopularAdvanced