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

VLSI circuit placement with rectilinear modules using three-layer force-directed self-organizing maps.

R I Chang¹, P Y Hsiao

¹Inst. of Inf. Sci., Acad. Sinica, Taipei.

IEEE Transactions on Neural Networks

|January 1, 1997

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

Dietary patterns and relationship to obesity-related health outcomes and mortality in adults 75 years of age or greater.

The journal of nutrition, health & aging·2013

Same author

Dietary patterns and diet quality among diverse older adults: the University of Alabama at Birmingham Study of Aging.

The journal of nutrition, health & aging·2013

Same author

Prenatal diagnosis of de novo interstitial deletion of proximal 4q by maternal serum screening for Down syndrome.

Prenatal diagnosis·1999

Same author

Unsupervised query-based learning of neural networks using selective-attention and self-regulation.

IEEE transactions on neural networks·1997

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 three-layer neural network optimizes circuit placement for complex rectilinear modules. This self-organizing map reduces wire length and module overlap, outperforming simulated annealing.

Area of Science:

Computer Science
Artificial Intelligence
VLSI Design

Background:

Circuit placement is a complex optimization problem, especially with arbitrarily shaped rectilinear modules.
Existing methods like simulated annealing can be time-consuming and may not yield optimal results.

Purpose of the Study:

To introduce a novel three-layer force-directed self-organizing map for rectilinear module placement.
To simultaneously minimize wire length and module overlap in circuit design.

Main Methods:

A three-layer neural network architecture with an additional hidden layer is proposed.
Hidden neurons model rectilinear modules by representing partitioned rectangles.
Collective computation among hidden neurons facilitates module interaction and placement convergence.

Related Experiment Videos

Main Results:

The proposed model effectively resolves the rectilinear module placement problem.
Placement results demonstrate a reduction in both wire length and module overlap.
The method shows superior performance compared to simulated annealing in terms of total wire length.

Conclusions:

The developed neural network model offers an efficient and effective solution for rectilinear module placement.
The approach successfully balances contradictory optimization criteria.
Further investigation into parameter tuning can yield even better placement solutions.