A unified framework of online learning algorithms for training recurrent neural networks

MaRDI QIDQ4969245zbMATH OpenFDO

Authors Owen Marschall, Cristina Savin, Kyung Hyun Cho

Publication date 5 October 2020

Full work available at URL https://arxiv.org/abs/1907.02649, https://jmlr.csail.mit.edu/papers/v21/19-562.html

zbMATH Keywords

online learningreal-time recurrent learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Online algorithms; streaming algorithms (68W27)

Recommendations

• On-line Gauss-Newton-based learning for fully recurrent neural networks
• Riemannian metrics for neural networks II: recurrent networks and learning symbolic data sequences
• scientific article; zbMATH DE number 7255038
• Towards a unified recurrent neural network theory: the uniformly pseudo-projection-anti-monotone net
• Timescale separation in recurrent neural networks

Cites work

• Reinforcement learning. An introduction
• Reservoir computing approaches to recurrent neural network training

Cited in

(6)

• Online AutoML: an adaptive AutoML framework for online learning
• scientific article; zbMATH DE number 2033224 (Why is no real title available?)
• scientific article; zbMATH DE number 5656321 (Why is no real title available?)
• scientific article; zbMATH DE number 2219463 (Why is no real title available?)
• scientific article; zbMATH DE number 1569110 (Why is no real title available?)
• Online learning dynamics of multilayer perceptrons with unidentifiable parameters

Describes a project that uses

Uses Software

• MNIST
• TensorFlow
• RMSprop

This page was built for publication: A unified framework of online learning algorithms for training recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969245)