A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Claude E. Shannon
Shannon extends his mathematical theory of communication to continuous signals and messages via a limiting process from the discrete case, revealing new effects and specializations.
Tareq Rasul, Sumesh Nair, Diane Robyn Kalendra, et al.
This perspective paper examines five benefits and five challenges of using ChatGPT in higher education through the lens of constructivist learning theory, proposing responsible use guidelines.
Liyuan Wang, Xingxing Zhang, Hang Su, et al.
A comprehensive survey of continual learning that bridges basic settings, theoretical foundations, representative methods, and practical applications, proposing a unified objective and taxonomy.
Unknown
Fortuna is an open-source library for uncertainty quantification in deep learning, addressing the gap between theory and practice.
Unknown
This paper critically examines the relationship between neural scaling laws and the role of theory in machine learning science.
Unknown
The paper applies large-N field theory to derive neural scaling laws and proposes solvable models that go beyond the ridgeless limit.
Unknown
Proposes a universal compression theory linking the lottery ticket hypothesis and neural scaling laws, showing how compression can significantly improve scaling laws.
Unknown
A statistical and approximation theory framework predicting neural scaling laws for transformers on intrinsically low-dimensional data, quantifying data and model scaling exponents.
Cheng Qian, Wenting Zhao, Liangwei Yang, et al.
This paper introduces test-time strong-to-weak capability transfer via inference-time harnesses, nearly doubling target model performance on Theory-of-Mind benchmarks without parameter updates.
Tiantian Guo, Tongpo Zhang, Eng Gee Lim, et al.
This review traces wavelet theory from construction to applications, highlighting rational wavelet transform advantages and the evolution of Wavelet Neural Networks.
Unknown
This review provides a practical introduction to neural operators for scientific computing, covering theory, applications, and their role as surrogates in forward modeling.
Unknown
This paper describes policy iteration for multi-agent reinforcement learning, focusing on an algorithm called Interconnected Learning Automata for Markov Games (MG-ILA).