Neural networks generalize on low complexity data
From MaRDI portal
Cites work
- A formal theory of inductive inference. Part I
- A logical calculus of the ideas immanent in nervous activity
- A provably stable neural network Turing machine with finite precision and time
- A universal prior for integers and estimation by minimum description length
- An introduction to Kolmogorov complexity and its applications
- An Introduction to Neural Data Compression
- Approximation by superpositions of a sigmoidal function
- Attention is Turing-complete
- Benign overfitting in linear regression
- Computational power of neural networks: a characterization in terms of Kolmogorov complexity
- Deep double descent: where bigger models and more data hurt*
- Deep learning: a statistical viewpoint
- Deep networks as denoising algorithms: sample-efficient learning of diffusion models in high-dimensional graphical models
- Flat Minima
- scientific article; zbMATH DE number 1304255 (Why is no real title available?)
- Multilayer feedforward networks are universal approximators
- Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- The collected works of Wassily Hoeffding. Ed. by N. I. Fisher and P. K. Sen
- The minimum description length principle in coding and modeling
- Understanding machine learning. From theory to algorithms
- Universal approximation bounds for superpositions of a sigmoidal function
This page was built for publication: Neural networks generalize on low complexity data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6844165)
