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

Data storage channel equalization using neural networks.

S K Nair¹, J Moon

¹IBM Almaden Res. Center, San Jose, CA.

IEEE Transactions on Neural Networks

|January 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

Cationic Polymer for Aligner and Oral Biofilm Removal via Osmotic Mechanism.

Journal of dental research·2025

Same author

Genomic and transcriptomic analyses of residual invasive triple-negative breast cancer after neoadjuvant chemotherapy in the prospective MIRINAE trial (a randomized phase II trial of adjuvant atezolizumab plus capecitabine compared to capecitabine; KCSG-BR18-21).

ESMO open·2025

Same author

Evolution of radiology staff perspectives during artificial intelligence (AI) implementation for expedited lung cancer triage.

Clinical radiology·2024

Same author

Measurement of 24-h continuous human CH<sub>4</sub> release in a whole room indirect calorimeter.

Journal of applied physiology (Bethesda, Md. : 1985)·2023

Same author

Search for an Excess of Electron Neutrino Interactions in MicroBooNE Using Multiple Final-State Topologies.

Physical review letters·2022

Same author

First Measurement of Energy-Dependent Inclusive Muon Neutrino Charged-Current Cross Sections on Argon with the MicroBooNE Detector.

Physical review letters·2022

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

Feedforward neural networks, specifically multilayer perceptrons, effectively equalize signals in thin-film magnetic recording channels. These networks improve data recovery and are suitable for VLSI implementation, reducing error probability.

Area of Science:

Electrical Engineering
Computer Science
Data Storage Technology

Background:

Thin-film magnetic recording channels suffer from non-Gaussian noise and nonlinear distortions, unlike typical communication systems.
Conventional equalizers struggle to accurately recover data under these challenging channel conditions.

Purpose of the Study:

To investigate the efficacy of feedforward neural networks, including multilayer perceptrons (MLPs), for signal equalization in thin-film magnetic recording.
To develop and evaluate novel training criteria for MLPs to minimize data error probability.
To assess the suitability of MLP variations for low-complexity Very Large Scale Integration (VLSI) implementation in data storage.

Main Methods:

Utilized multilayer perceptrons (MLPs) and their simplified variations as feedforward neural network equalizers.

Related Experiment Videos

Developed a novel training criterion specifically designed to reduce the probability of error in recovered digital data.

Validated the equalization performance using both experimental data and a software recording channel simulator with thin-film disk and magnetoresistive head models.

Main Results:

Feedforward neural networks demonstrated superior performance in data recovery compared to conventional equalizers.
Simplified MLP equalizer variations are well-suited for low-complexity VLSI implementation, crucial for data storage systems.
The novel training criterion effectively reduced the probability of error for recovered digital data.

Conclusions:

Feedforward neural networks, particularly MLPs, offer a significant advancement in equalizing complex signals from thin-film magnetic recording channels.
The developed MLP variations and training methods provide a practical and efficient solution for high-performance data storage systems.
This research contributes to improved data integrity and recovery in magnetic recording technology.