Learning to learn using gradient descent

DOI10.1007/3-540-44668-0_13MaRDI QIDQ4783863zbMATH OpenFDO

Authors Sepp Hochreiter, A. Steven Younger, Peter R. Conwell

Publication date 9 December 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2130/21300087

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• scientific article; zbMATH DE number 2033143
• Complexity measures for meta-learning and their optimality
• Gradient descent learns linear dynamical systems
• Learning gradients by a gradient descent algorithm
• scientific article; zbMATH DE number 2044698

Cited in

(24)

• Temporal-kernel recurrent neural networks
• Retail sales forecasting with meta-learning
• Machine learning for combinatorial optimization: a methodological tour d'horizon
• Stateless neural meta-learning using second-order gradients
• A metalearning approach for physics-informed neural networks (PINNs): application to parameterized PDEs
• Gradient methods for optimizing metaparameters in the knowledge distillation problem
• scientific article; zbMATH DE number 19772 (Why is no real title available?)
• scientific article; zbMATH DE number 2033143 (Why is no real title available?)
• scientific article; zbMATH DE number 2044698 (Why is no real title available?)
• Divide-and-conquer checkpointing for arbitrary programs with no user annotation
• The dropout learning algorithm
• scientific article; zbMATH DE number 7626770 (Why is no real title available?)
• Progress in Artificial Intelligence
• Machine Learning: ECML 2004
• Learning with Limited Samples: Meta-Learning and Applications to Communication Systems
• Deep Learning for Marginal Bayesian Posterior Inference with Recurrent Neural Networks
• An overview of stochastic quasi-Newton methods for large-scale machine learning
• MGIC: Multigrid-in-Channels Neural Network Architectures
• Automated Deep Learning: Neural Architecture Search Is Not the End
• Tutorial on Amortized Optimization
• A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms
• Are LSTMs good few-shot learners?
• Model-agnostic Hessian-free meta-policy optimization via zeroth-order estimation: a linear quadratic regulator perspective
• Bayes meets Bernstein at the meta level: an analysis of fast rates in meta-learning with PAC-Bayes

This page was built for publication: Learning to learn using gradient descent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4783863)