Search research articles

Search research articles

Related Experiment Video

Updated: Mar 27, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Unsupervised Feature Learning Classification With Radial Basis Function Extreme Learning Machine Using Graphic

Dao Lam, Donald Wunsch

IEEE Transactions on Cybernetics

|January 8, 2016

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

Knowledge Distillation-Based TinyML Model for Breast Cancer Detection Using Real and Wasserstein GAN-Generated Microwave Imaging Data.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Same author

Phantom-based Quality Assurance of a Clinical Dose Accumulation Technique Used in an Online Adaptive Radiation Therapy Platform.

Advances in radiation oncology·2023

Same author

Robustness and reproducibility of an artificial intelligence-assisted online segmentation and adaptive planning process for online adaptive radiation therapy.

Journal of applied clinical medical physics·2022

Same author

Targetability of cervical cancer by magnetic resonance-guided high-intensity focused ultrasound (MRgHIFU)-mediated hyperthermia (HT) for patients receiving radiation therapy.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2021

Same author

Long-term Inter-protocol kV CBCT image quality assessment for a ring-gantry linac via automated QA approach.

Biomedical physics & engineering express·2021

Same author

Exploratory Analysis of Concussion Recovery Trajectories using Multi-modal Assessments and Serum Biomarkers.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2020

Same journal

An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

IEEE transactions on cybernetics·2026

Same journal

A Quantum Self-Attention Neural Network Model on Quantum Circuits.

IEEE transactions on cybernetics·2026

Same journal

Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

IEEE transactions on cybernetics·2026

Same journal

A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

IEEE transactions on cybernetics·2026

Same journal

Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

IEEE transactions on cybernetics·2026

Same journal

Digital Redesign-Based Interval State Estimation for Continuous Systems With Aperiodic Discrete Measurements.

IEEE transactions on cybernetics·2026

See all related 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

This study introduces a novel unsupervised feature learning (UFL) method combined with a fast radial basis function (RBF) extreme learning machine (ELM) to enhance machine learning speed and accuracy. A custom CUDA kernel significantly accelerates computations, achieving up to 20x speedup.

Area of Science:

Machine Learning
Artificial Intelligence
Computer Science

Background:

Increasing data complexity challenges traditional learning algorithms, demanding improvements in both accuracy and speed.
Unsupervised feature learning (UFL) offers a promising avenue for extracting meaningful patterns from large datasets without labeled data.

Purpose of the Study:

To develop an efficient mechanism for training unsupervised learning features to enhance the performance of learning algorithms.
To improve both the accuracy and computational speed of machine learning models when dealing with large and complex datasets.

Main Methods:

Features were learned using an unsupervised feature learning (UFL) algorithm.
These learned features were then trained using a fast radial basis function (RBF) extreme learning machine (ELM).

Related Experiment Videos

Last Updated: Mar 27, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

A custom Compute Unified Device Architecture (CUDA) kernel was developed to leverage GPU parallel processing for accelerating RBF kernel computations within the ELM.

Main Results:

The combined UFL RBF ELM approach demonstrated high accuracy on benchmark datasets (CIAR and NIST).
The CUDA implementation of the RBF kernel achieved a significant speedup, performing up to 20 times faster than CPU-based computations.
The parallel approach also outperformed naive parallel methods, indicating efficient scalability.

Conclusions:

The proposed UFL RBF ELM framework effectively addresses the speed-accuracy tradeoff in machine learning for large datasets.
The CUDA optimization provides substantial computational acceleration, making complex models more practical for real-world applications.
This research contributes a novel and efficient method for unsupervised feature learning and model training, particularly beneficial for big data analytics.