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

Search research articles

Related Experiment Videos

Using localizing learning to improve supervised learning algorithms.

S Weaver¹, L Baird, M Polycarpou

¹GenomatixUSA, Cincinnati, OH 45221, USA. scott.weaver@uc.edu

IEEE Transactions on Neural Networks

|February 6, 2008

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

Physical review letters·2024

Same author

Lawson Criterion for Ignition Exceeded in an Inertial Fusion Experiment.

Physical review letters·2022

Same author

Unchecked immunity: a unique case of sequential immune-related adverse events with Pembrolizumab.

Journal for immunotherapy of cancer·2019

Same author

The Use of Nisin as a Preservative in Crumpets.

Journal of food protection·2019

Same author

Assembly of high-areal-density deuterium-tritium fuel from indirectly driven cryogenic implosions.

Physical review letters·2012

Same author

Antibodies to metabotropic glutamate receptor 5 in the Ophelia syndrome.

Neurology·2011

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces a novel algorithm to reduce interference in neural networks, preventing unlearning and accelerating training. The method optimizes network weights to minimize both approximation error and interference for more efficient learning.

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

Slow learning in neural networks is often caused by interference, where learning new information leads to forgetting previously learned data.
This unlearning phenomenon hinders the efficiency and effectiveness of neural network training.

Purpose of the Study:

To develop an algorithm that mitigates interference in neural network function approximators.
To reduce the potential for future unlearning during the network's learning process.

Main Methods:

Developed a novel algorithm to adjust network weights by minimizing a biobjective cost function.
The cost function combines approximation error with a measure of interference.
Analyzed the algorithm's convergence properties to demonstrate its effectiveness in reducing future unlearning.

Related Experiment Videos

Main Results:

The algorithm successfully reduces future unlearning by modifying network weights.
Demonstrated that reduced interference leads to more efficient learning through a simple example.
Simulations confirmed that the new learning algorithm accelerates training across various scenarios.

Conclusions:

The proposed algorithm effectively combats interference in neural networks, leading to faster and more robust learning.
This method can be applied during online learning or to pre-condition networks for enhanced interference immunity.