Consideration on the learning efficiency of multiple-layered neural networks with linear units
From MaRDI portal
Publication:6190543
DOI10.1016/j.neunet.2024.106132WikidataQ129749508 ScholiaQ129749508MaRDI QIDQ6190543
Publication date: 5 March 2024
Published in: Neural Networks (Search for Journal in Brave)
algebraic geometrysingular learning theorymultiple-layered neural networks with linear unitsresolution map
Learning and adaptive systems in artificial intelligence (68T05) Divisors, linear systems, invertible sheaves (14C20)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Consideration on singularities in learning theory and the learning coefficient
- Marginal likelihood and model selection for Gaussian latent tree and forest models
- B-functions and holonomic systems. Rationality of roots of B-functions
- Estimating the dimension of a model
- Equations of states in singular statistical estimation
- Asymptotic behavior of exchange ratio in exchange Monte Carlo method
- Stochastic complexities of reduced rank regression in Bayesian estimation
- Resolution of singularities of an algebraic variety over a field of characteristic zero. I
- Algebraic Analysis for Nonidentifiable Learning Machines
- A Bayesian Learning Coefficient of Generalization Error and Vandermonde Matrix-Type Singularities
- Algebraic Geometry and Statistical Learning Theory
- Universal coding, information, prediction, and estimation
- Singularities of pairs via jet schemes
- Singularities of Pairs
- An asymptotic approximation of the marginal likelihood for general Markov models
- A new look at the statistical model identification
This page was built for publication: Consideration on the learning efficiency of multiple-layered neural networks with linear units
