Search research 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

Search research articles

Related Experiment Videos

Analog neural network for support vector machine learning.

Renzo Perfetti, Elisa Ricci

IEEE Transactions on Neural Networks

|July 22, 2006

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

Vocabulary-Free Image Classification and Semantic Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

3D Object Detection From Images for Autonomous Driving: A Survey.

IEEE transactions on pattern analysis and machine intelligence·2023

Same author

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2023

Same author

Revisiting Viewing Graph Solvability: An Effective Approach Based on Cycle Consistency.

IEEE transactions on pattern analysis and machine intelligence·2022

Same author

Uncertainty-Aware Contrastive Distillation for Incremental Semantic Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2022

Same author

Variational Structured Attention Networks for Deep Visual Representation Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

A novel analog neural network simplifies support vector machine learning using a dual quadratic programming formulation. This approach offers a more efficient circuit design compared to existing neural network solutions.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Support Vector Machines (SVM) are powerful supervised learning models used for classification and regression.
Solving SVM optimization problems often involves complex quadratic programming.
Existing neural network solutions for SVM can be circuit-intensive.

Discussion:

This study introduces an analog neural network architecture for SVM.
The network leverages a partially dual formulation of the quadratic programming problem.
This formulation leads to a simplified circuit implementation.

Key Insights:

The proposed analog neural network offers a more efficient hardware implementation for SVM.
Computer simulations validate the network's effectiveness on benchmark datasets.

Related Experiment Videos

This work contributes to the development of efficient hardware accelerators for machine learning.

Outlook:

Further research can explore scaling this architecture for larger datasets.
Investigating the network's performance with different SVM kernels is warranted.
Potential applications include embedded systems and real-time machine learning tasks.