Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning document semantic representation with hybrid deep belief network.

Yan Yan1, Xu-Cheng Yin1, Sujian Li2

  • 1Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China.

Computational Intelligence and Neuroscience
|April 17, 2015
PubMed
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

Inferior vena cava respiratory variability changes during jet ventilation in rigid bronchoscopy: a prospective self-controlled study.

BMC anesthesiology·2026
Same author

Generation of gamma photons carrying transverse orbital angular momentum driven by a spatiotemporal optical vortex laser.

Optics express·2026
Same author

Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation.

Nature communications·2026
Same author

Anesthetic management for thoracoscopic bilateral bullectomy in a patient with stage III pneumoconiosis, bilateral giant bullous emphysema, stage IV chronic obstructive pulmonary disease and profoundly impaired pulmonary function: a rare case report.

AME case reports·2026
Same author

Efficacy and safety of supraglottic jet oxygenation and ventilation in Chinese patients undergoing bronchoscopic procedures: a systematic review and meta-analysis.

Frontiers in medicine·2026
Same author

Research on liver cancer pathology image recognition based on deep learning image processing.

Scientific reports·2026
Same journal

RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
See all related articles

This study introduces a Hybrid Deep Belief Network (HDBN) for improved document semantic representation. The HDBN model enhances document classification and retrieval by effectively learning semantic features.

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Information Retrieval

Background:

  • High-level semantic representation is crucial for document classification and retrieval.
  • Learning effective document semantic representation remains an open challenge in NLP and IR.

Purpose of the Study:

  • To propose a novel Hybrid Deep Belief Network (HDBN) for learning document semantic representation.
  • To explore various input strategies for semantic distributed representation.

Main Methods:

  • The proposed Hybrid Deep Belief Network (HDBN) integrates Deep Boltzmann Machines (DBMs) in lower layers and Deep Belief Networks (DBNs) in upper layers.
  • DBMs utilize undirected connections for successful node state sampling and noise reduction.
  • DBNs enhance in-depth document abstraction for sufficient semantic learning.

Related Experiment Videos

Main Results:

  • The HDBN model demonstrates superior performance in learning document semantic representation.
  • Utilizing word embeddings as input significantly outperforms single-word inputs.
  • Experimental results validate the effectiveness of the proposed hybrid approach.

Conclusions:

  • The Hybrid Deep Belief Network (HDBN) offers an effective solution for learning document semantic representations.
  • The hybrid architecture combining DBM and DBN capabilities enhances feature extraction.
  • Word embeddings are a more effective input strategy for semantic distributed representation in this model.