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

A compact 3D VLSI classifier using bagging threshold network ensembles.

A Bermak¹, D Martinez

¹Electr. and Electron. Eng. Dept., Hong Kong Univ. of Sci. and Technol., Kowloon, China.

IEEE Transactions on Neural Networks

|February 5, 2008

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

Ultra-fast single-crystal CVD diamonds in the particle time-of-flight (PTOF) detector for low yield burn-history measurements on the NIF (invited).

The Review of scientific instruments·2025

Same author

Barriers to early detection: Insurance denials for breast MRI screening in women with germline BRCA1/2 mutations.

Gynecologic oncology·2025

Same author

Distribution and Characteristics of Congenital Cardiac Surgery Centers within Bangladesh.

Mymensingh medical journal : MMJ·2024

Same author

Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

Physical review letters·2024

Same author

Lawson Criterion for Ignition Exceeded in an Inertial Fusion Experiment.

Physical review letters·2022

Same author

The fasted and post-prandial physiological responses of the Patagonian blennie Eleginops maclovinus.

Comparative biochemistry and physiology. Part A, Molecular & integrative physiology·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 compact 3D multiprecision very large-scale integration (VLSI) chip implements bagging ensembles for real-time pattern recognition. This hardware efficiently processes data, overcoming memory and computation limitations for portable applications.

Area of Science:

Electrical Engineering
Computer Science
Artificial Intelligence

Background:

Bagging ensembles enhance classifier performance but demand significant computational resources.
Portable real-time pattern recognition applications are constrained by memory and computation limitations.

Purpose of the Study:

To develop a compact three-dimensional (3D) multiprecision very large-scale integration (VLSI) implementation of a bagging ensemble.
To address the memory and computation drawbacks of traditional bagging ensembles for portable real-time applications.

Main Methods:

Decision trees were implemented as threshold networks using threshold logic units (TLUs).
A 3D VLSI circuit was fabricated using 0.7-/spl mu/m CMOS technology and MCM-V micro-packaging.
The chip integrates up to 192 TLUs, operating at speeds up to 48 GCPPS within a 2x2x0.7 cm/sup 3/ volume.

Related Experiment Videos

Main Results:

The 3D chip demonstrates high programmability and flexibility for efficient resource utilization and reduced power consumption.
Successful operation was validated across various precisions and ensemble sizes.
The implementation was successfully applied to an electronic nose application.

Conclusions:

The developed 3D VLSI bagging ensemble offers a compact and efficient solution for real-time pattern recognition.
This hardware approach overcomes the limitations of conventional software-based ensembles, enabling new portable applications.
The chip's design facilitates power-efficient operation and adaptability to diverse pattern recognition tasks.