An Accelerating Learning Algorithm for Block-Diagonal Recurrent Neural Networks

13 years 10 months ago

Download www.teiser.gr

An efficient training method for block-diagonal recurrent neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static models, in order to be applied to dynamic systems. A comparative analysis with a series of algorithms and recurrent models is given, indicating the effectiveness of the proposed learning approach.

Paris A. Mastorocostas, Dimitris N. Varsamis, Cons

Real-time Traffic

CIMCA 2005 | Efficient Training Method | Recurrent Models | Recurrent Neural Networks |

claim paper

» Online SymbolicSequence Prediction with DiscreteTime Recurrent Neural Networks

» Practical Recurrent Learning PRL in the Discrete Time Domain

» An algorithm for the addition of timedelayed connections to recurrent neural networks

» Autonomous learning algorithm for fully connected recurrent networks

» Recurrent Neural Kalman Filter Identification and Indirect Adaptive Control of a Continuou...

» Coevolving recurrent neurons learn deep memory POMDPs

» Opposite Transfer Functions and Backpropagation Through Time

» Prediction Using Recurrent Neural Network Based Fuzzy Inference system by the Modified Bee...

Post Info
More Details (n/a)

Added	24 Jun 2010
Updated	24 Jun 2010
Type	Conference
Year	2005
Where	CIMCA
Authors	Paris A. Mastorocostas, Dimitris N. Varsamis, Constantinos A. Mastorocostas, Ioannis Rekanos

Comments (0)

Sciweavers

An Accelerating Learning Algorithm for Block-Diagonal Recurrent Neural Networks

CIMCA 2005 | Efficient Training Method | Recurrent Models | Recurrent Neural Networks |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers