KAN: Kolmogorov-Arnold Networks
Paper
•
2404.19756
•
Published
•
108
Theory
-
-
The Platonic Representation Hypothesis
Paper • 2405.07987 • Published • 2 -
The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Paper • 2304.05366 • Published • 1 -
Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
Paper • 1512.02479 • Published • 1 -
Large Language Models as Markov Chains
Paper • 2410.02724 • Published • 31 -
Neural Machine Translation by Jointly Learning to Align and Translate
Paper • 1409.0473 • Published • 4 -
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models
Paper • 2310.17086 • Published • 1 -
Cross-Entropy Loss Functions: Theoretical Analysis and Applications
Paper • 2304.07288 • Published • 1 -
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Paper • 2410.19750 • Published • 1 -
The Super Weight in Large Language Models
Paper • 2411.07191 • Published • 2