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

The New ERA in Supervised Learning.

JOHN G. TAYLOR¹, ADRIAN J. SHEPHERD, DENISE GORSE

¹King's College, London, UK

Neural Networks : the Official Journal of the International Neural Network Society

|March 1, 1997

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

Investigating the predictive power of seismic statistical features using ensemble learning.

PloS one·2026

Same author

Cryptocurrency price drivers: Wavelet coherence analysis revisited.

PloS one·2018

Same author

Morphological aspects of oligomeric protein structures.

Progress in biophysics and molecular biology·2005

Same author

Neural Networks for Predicting Conditional Probability Densities: Improved Training Scheme Combining EM and RVFL.

Neural networks : the official journal of the International Neural Network Society·2003

Same author

A novel approach to the recognition of protein architecture from sequence using Fourier analysis and neural networks.

Proteins·2002

Same author

Application of a chaperone-based refolding method to two- and three-dimensional off-lattice protein models.

Biopolymers·2002

Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Conventional supervised learning methods often get stuck in local minima. A new Expanded Range Approximation (ERA) technique helps supervised learning find the global minimum, avoiding sub-optimal solutions.

Area of Science:

Machine Learning
Optimization Techniques

Background:

Supervised learning algorithms commonly encounter the local minima problem.
Second-order optimization methods like conjugate gradient and quasi-Newton are prone to suboptimal solutions.

Purpose of the Study:

To introduce a novel technique, Expanded Range Approximation (ERA), to overcome local minima in supervised learning.
To enable supervised learning methods to consistently find the global minimum of the error function.

Main Methods:

Implementation of Expanded Range Approximation (ERA).
Utilizing a homotopy on the range of target outputs within the ERA framework.

Main Results:

ERA significantly reduces the likelihood of supervised learning being trapped in local minima.

Related Experiment Videos

The technique facilitates the discovery of the global minimum in almost all tested cases.

Conclusions:

Expanded Range Approximation (ERA) offers a robust solution to the persistent local minima problem in supervised learning.
ERA enhances the reliability and performance of supervised learning models by ensuring convergence to the global optimum.