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

Convergence analysis of cascade error projection--an efficient learning algorithm for hardware implementation.

T A Duong1, A R Stubberud

  • 1Center for Space Microelectronics Technology, Jet Propulsion Laboratory, California Institute of Technology, Pasadena 91109, USA.

International Journal of Neural Systems
|September 30, 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

Response to Thakker et al, "Bridging the dermatological divide: The ethical deployment of artificial intelligence in low-resource settings".

Journal of the American Academy of Dermatology·2025
Same author

A new <i>Paecilomyces</i> from wooden utility poles in South Africa.

Fungal systematics and evolution·2024
Same author

Characterisation of the mating-type loci in species of Elsinoe causing scab diseases.

Fungal biology·2023
Same author

Generic boundaries in the <i>Ophiostomatales</i> reconsidered and revised.

Studies in mycology·2022
Same author

Skin cancer and COVID-19: was the diagnosis safeguarded by teledermatology? a study on 1229 cases.

Journal of the European Academy of Dermatology and Venereology : JEADV·2022
Same author

Population genomics reveals historical and ongoing recombination in the <i>Fusarium oxysporum</i> species complex.

Studies in mycology·2022
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

We introduce a mathematical foundation for cascading neural networks, ensuring convergence via Liapunov criteria. A novel Cascade Error Projection (CEP) algorithm enables efficient hardware learning and faster training for these networks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Cascading architecture neural networks offer a flexible approach to modeling complex relationships.
  • Existing cascade correlation learning algorithms lack a rigorous mathematical foundation and efficient hardware implementation.
  • The convergence properties of cascade architecture neural networks require further theoretical analysis.

Purpose of the Study:

  • To establish a mathematical foundation and convergence analysis for cascading architecture neural networks.
  • To introduce an efficient hardware learning algorithm, Cascade Error Projection (CEP), derived from this mathematical analysis.
  • To evaluate the performance of CEP in terms of training speed, hardware simplicity, and weight quantization.

Main Methods:

Related Experiment Videos

  • Developed a mathematical framework for cascading architecture neural networks, including convergence analysis using Liapunov criteria in an added hidden unit domain.
  • Derived the Cascade Error Projection (CEP) algorithm as an efficient hardware learning method, optimizing weight determination and training processes.
  • Investigated CEP's performance on 5- to 8-bit parity and chaotic time series prediction tasks, analyzing the impact of weight quantization.

Main Results:

  • Convergence of cascade architecture neural networks is mathematically assured by satisfying Liapunov criteria.
  • The proposed Cascade Error Projection (CEP) algorithm offers faster training and simpler hardware implementation compared to existing methods.
  • CEP demonstrates effective learning with 4-bit or higher weight quantization, and can compensate for lower bit resolution with additional hidden units.

Conclusions:

  • The mathematical foundation validates the convergence of cascade architecture neural networks.
  • Cascade Error Projection (CEP) provides an efficient and practical hardware learning solution for these networks.
  • CEP is robust to weight quantization, making it suitable for resource-constrained hardware implementations.