A simultaneous perturbation weak derivative estimator for stochastic neural networks

DOI10.1007/S10287-019-00357-1MaRDI QIDQ2010380zbMATH OpenOpenAlexFDO

Authors Thomas Flynn, Felisa J. Vázquez-Abad

Publication date 27 November 2019

Published in Computational Management Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1905.01350

Mathematics Subject Classification ID

Operations research and management science (90Bxx)

Recommendations

• Forward sensitivity analysis for contracting stochastic systems
• Monte Carlo gradient estimation in machine learning
• The convergence of stochastic gradient algorithms applied to learning in neural networks
• scientific article; zbMATH DE number 774841
• Convergence of an online gradient method for feedforward neural networks with stochastic inputs.

Cites work

• scientific article; zbMATH DE number 1005357 (Why is no real title available?)
• A Fast Learning Algorithm for Deep Belief Nets
• A logical calculus of the ideas immanent in nervous activity
• Collective properties of neural networks: A statistical physics approach
• Conditioning properties of the stationary distribution for a Markov chain
• Connectionist learning of belief networks
• Gradient estimates for the performance of Markov chains and discrete event processes
• Gradient estimation for discrete-event systems by measure-valued differentiation
• Learning by parallel Boltzmann machines
• Learning representations by back-propagating errors
• Measure-valued differentiation for Markov chains
• Measure-valued differentiation for random horizon problems
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• On-Line Optimization of Simulated Markovian Processes
• Stochastic approximation methods for constrained and unconstrained systems
• Taylor series expansions for stationary Markov chains
• The existence of persistent states in the brain
• The relations among potentials, perturbation analysis, and Markov decision processes
• stochastic quasigradient methods and their application to system optimization^†

Cited in

(3)

• Simultaneous perturbation for single hidden layer networks -- cascade learning
• Efficient estimation of average derivatives in NPIV models: simulation comparisons of neural network estimators
• A Simultaneous Perturbation Weak Derivative Estimator for Stochastic Neural Networks

Describes a project that uses

Uses Software

• darch

This page was built for publication: A simultaneous perturbation weak derivative estimator for stochastic neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2010380)