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

Binary neural network training algorithms based on linear sequential learning.

Di Wang1, Narendra S Chaudhari

  • 1School of Computing Engineering, Block N4-2a-32, 50 Nanyang Avenue, Nanyang Technological University, Singapore 639798, Singapore. wangdi@pmail.ntu.edu.sg

International Journal of Neural Systems
|December 4, 2003
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

A new Prenylated Flavonoid induces G0/G1 arrest and apoptosis through p38/JNK MAPK pathways in Human Hepatocellular Carcinoma cells.

Scientific reports·2017
Same author

The purine-rich element-binding protein ChPur-α negatively regulates Hsc70 transcription in Crassostrea hongkongensis.

Cell stress & chaperones·2017
Same author

Improved antitumor effect of ionizing radiation in combination with rapamycin for treating nasopharyngeal carcinoma.

Oncology letters·2017
Same author

Roles of Cells from the Arterial Vessel Wall in Atherosclerosis.

Mediators of inflammation·2017
Same author

Metabolic and microbial signatures in rat hepatocellular carcinoma treated with caffeic acid and chlorogenic acid.

Scientific reports·2017
Same author

Arsenic removal in aqueous solution by a novel Fe-Mn modified biochar composite: Characterization and mechanism.

Ecotoxicology and environmental safety·2017
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

Binary Neural Network learning is improved by finding larger linearly separable subsets. New Multi-Core Learning (MCL) and MCETL algorithms simplify weight computation and hidden layer construction for binary neural networks.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Binary Neural Networks (BNNs) face challenges in identifying optimal linearly separable subsets for effective learning.
  • Efficiently constructing BNNs requires addressing the complexity of weight and threshold calculations.

Purpose of the Study:

  • To address the key problem of finding larger linearly separable subsets in Binary Neural Network learning.
  • To propose novel algorithms that simplify the construction of BNNs.

Main Methods:

  • Proved lemmas related to linear separability.
  • Developed Multi-Core Learning (MCL) and Multi-Core Expand-and-Truncate Learning (MCETL) algorithms for BNN construction.

Main Results:

Related Experiment Videos

  • The proposed MCL and MCETL algorithms simplify the equations for computing weights and thresholds.
  • These algorithms lead to the creation of simpler hidden layers in BNNs.

    • Conclusions:

    • MCL and MCETL offer a more efficient approach to Binary Neural Network construction.
    • The simplification in computation and structure contributes to more manageable BNN models.