Elman Backpropagation as Reinforcement for Simple Recurrent Networks

DOI10.1162/NECO.2007.19.11.3108MaRDI QIDQ5441309zbMATH OpenOpenAlexWikidataFDO

Authors André Grüning

Publication date 11 February 2008

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL http://epubs.surrey.ac.uk/22857/23/neco.2007.19.11.3108.pdf

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Organization of the state space of a simple recurrent network before and after training on recursive linguistic structures
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Simple recurrent networks learn context-free and context-sensitive languages by counting.
• Comparing simple recurrent networks and n-grams in a large corpus
• Backpropagation

Cites work

• Attention-Gated Reinforcement Learning of Internal Representations for Classification
• Dynamical recognizers: real-time language recognition by analog computers
• Predicting the future of discrete sequences from fractal representations of the past
• Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
• Simple recurrent networks learn context-free and context-sensitive languages by counting.
• Stack-like and queue-like dynamics in recurrent neural networks
• Synaptic noise as a means of implementing weight-perturbation learning
• The calculi of emergence: Computation, dynamics and induction
• The Crystallizing Substochastic Sequential Machine Extractor: CrySSMEx

Cited in

(2)

• Supervised learning in multilayer spiking neural networks
• Learning spatiotemporally encoded pattern transformations in structured spiking neural networks

This page was built for publication: Elman Backpropagation as Reinforcement for Simple Recurrent Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5441309)