Search research articles

Search research articles

Related Experiment Video

Updated: Mar 8, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

A Telescopic Binary Learning Machine for Training Neural Networks.

Mauro Brunato, Roberto Battiti

IEEE Transactions on Neural Networks and Learning Systems

|January 24, 2017

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

Forecasting daily total pollen concentrations on a global scale.

Allergy·2024

Same author

A temporally and spatially explicit, data-driven estimation of airborne ragweed pollen concentrations across Europe.

The Science of the total environment·2023

Same author

Feature Selection Based on the Neighborhood Entropy.

IEEE transactions on neural networks and learning systems·2018

Same author

Hybridization of decomposition and local search for multiobjective optimization.

IEEE transactions on cybernetics·2014

Same author

Active learning of Pareto fronts.

IEEE transactions on neural networks and learning systems·2014

Same author

MOEA/D-ACO: a multiobjective evolutionary algorithm using decomposition and AntColony.

IEEE transactions on cybernetics·2013

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

This study introduces a novel binary learning machine (BLM) algorithm for neural network training. This adaptive, multiscale approach enhances search speed and generalization performance in machine learning tasks.

Area of Science:

Machine Learning
Artificial Intelligence
Computational Neuroscience

Background:

Neural network training is computationally intensive.
Optimizing neural network performance requires efficient algorithms.
Binary representations offer potential for computational savings.

Purpose of the Study:

To propose a novel algorithm for training neural networks using binary representations.
To investigate the impact of various parameters on the binary learning machine (BLM) algorithm.
To develop an adaptive, multiscale approach for improved search efficiency and generalization.

Main Methods:

Multiscale stochastic local search with binary representation.
Analysis of neighborhood evaluation strategies and weight mapping parameters.

Related Experiment Videos

Last Updated: Mar 8, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Telescopic multiscale local search with adaptive bit-incrementing.

Main Results:

The proposed adaptive multiscale BLM accelerates search and finds better local minima.
Dynamic control over the number of bits improves generalization performance.
The algorithm demonstrates effectiveness on nonlinear artificial and real-world tasks.

Conclusions:

The binary learning machine (BLM) offers an efficient and effective method for neural network training.
Adaptive multiscale strategies are crucial for optimizing binary learning algorithms.
BLM shows promise for diverse applications, including feedback control systems.