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

Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using

R S Neville1, T J Stonham, R J Glover

  • 1School of Computing Information Systems and Mathematics, South Bank University, London, UK.

Neural Networks : the Official Journal of the International Neural Network Society
|August 10, 2000
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

Transformations of sigma-pi nets: obtaining reflected functions by reflecting weight matrices.

Neural networks : the official journal of the International Neural Network Society·2002
Same author

Racial attitudes of preschoolers: age, race of examiner, and child-care setting.

Psychological reports·1997
Same author

Religiosity in adolescence and young adulthood: implications for identity formation.

Psychological reports·1996
Same author

Generalization in multi-layer networks of Sigma-pi units.

IEEE transactions on neural networks·1995
Same author

Using moral and epistemological reasoning as predictors of prejudice.

The Journal of social psychology·1994
Same author

Applying neopiagetian theory to the moral reasoning process.

Psychological reports·1990
Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

EEG fine-grained visual semantic decoding via a multimodal framework.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel digital methodology for sigma-pi neural units, enabling high-accuracy function mapping with quantized weights and activations. The approach enhances accuracy by expanding internal state space and uses ring memories for efficient bit-stream implementation.

Area of Science:

  • Artificial Intelligence
  • Digital Neural Networks
  • Microelectronic Technology

Background:

  • Artificial neural networks require accurate real-valued function mapping.
  • Existing sigma-pi units have limitations in accuracy and hardware implementation.
  • Gurney's sigma-pi neural model provides a foundation for structured hypercubes.

Purpose of the Study:

  • To present a digital methodology for sigma-pi neural units achieving high-accuracy function mapping.
  • To enable quantization of weights to 8-bits and activations to 9-bits.
  • To improve accuracy by expanding the internal state space of sigma-pi units.

Main Methods:

  • Partially pre-calculating weight updates in the backpropagation learning regime.
  • Implementing neural units in a digital formulation with quantized weights and activations.

Related Experiment Videos

  • Utilizing novel ring memory implementation for bit-streams instead of shift registers.
  • Expanding the internal state space of sigma-pi units to increase bandwidth.

    • Main Results:

    • Achieved accuracies better than 1% for target output functions (MSE < 0.0001).
    • Demonstrated high-accuracy real-valued function mapping using RAM-based sigma-pi units.
    • Successfully mapped bit-streams to RAM using ring memories for simplified hardware implementation.
    • Showcased the ability of trained sigma-pi units to generalize continuous functions.

    Conclusions:

    • The proposed digital methodology enables highly accurate real-valued function mapping with sigma-pi neural units.
    • The use of quantized weights and expanded state space offers efficient and accurate neurocomputing.
    • Ring memory implementation simplifies hardware design for bit-stream processing in neural networks.