Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Three-dimensional video compression using subband/wavelet transform with lower buffering requirements.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008

Same author

A comparison between neural-network forecasting techniques--case study: river flow forecasting.

IEEE transactions on neural networks·2008

Same author

Bankruptcy prediction for credit risk using neural networks: a survey and new results.

IEEE transactions on neural networks·2008

Same author

An algorithmic approach to adaptive state filtering using recurrent neural networks.

IEEE transactions on neural networks·2008

Same author

Multi-step-ahead prediction using dynamic recurrent neural networks.

Neural networks : the official journal of the International Neural Network Society·2001

Same author

A new algorithm for learning in piecewise-linear neural networks.

Neural networks : the official journal of the International Neural Network Society·2000

Search research articles

Related Experiment Video

Updated: Jun 30, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

New results on recurrent network training: unifying the algorithms and accelerating convergence.

A F Atiya¹, A G Parlos

¹Learning Systems Group, Department of Electrical Engineering, California Institute of Technology, Pasadena, CA 91125, USA. amir@work.caltech.edu

IEEE Transactions on Neural Networks

|February 6, 2008

Summary

This study unifies recurrent network training methods by showing they solve a single matrix equation. A new algorithm offers lower complexity and faster convergence, with an online version available.

Related Experiment Videos

Last Updated: Jun 30, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Artificial Intelligence
Machine Learning
Deep Learning

Background:

Efficient training of recurrent neural networks (RNNs) is a significant research challenge.
Existing training methods, primarily focused on gradient computation, fall into five main categories.

Purpose of the Study:

To unify existing recurrent network training approaches through a novel derivation.
To develop a new, computationally efficient algorithm for training recurrent networks.

Main Methods:

A unifying derivation demonstrating that five major training approaches are solutions to a single matrix equation.
Development of a new algorithm based on approximating the error gradient.

Main Results:

The novel formulation reveals that existing methods are variations of solving one matrix equation.
The new algorithm exhibits lower computational complexity for weight updates and achieves faster convergence to the error minimum.
An online version of the algorithm was developed, enabling recursive updates of the error gradient approximation.

Conclusions:

The unified framework simplifies the understanding of recurrent network training.
The new algorithm and its online variant offer significant improvements in efficiency and speed for training recurrent networks.