Search research articles

Related Concept Videos

Propagation of Action Potentials

Propagation of Action Potentials

The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...

Distributed Loads: Problem Solving

Distributed Loads: Problem Solving

Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Comparative evaluation of variations in torque expression in maxillary incisor and canine using different bracket prescriptions placed at different crown levels by finite element (FE) method: An <i>in-vitro</i> analysis.

Journal of orthodontic science·2024

Same author

Evaluation of Change in Surface Enamel Microhardness in Patients Undergoing Fixed Orthodontic Appliance Therapy - A Randomized Control Trial.

Journal of pharmacy & bioallied sciences·2022

Same author

MR-guided parenchymal delivery of adeno-associated viral vector serotype 5 in non-human primate brain.

Gene therapy·2017

Same author

The efficacy of different pre- and post-operative analgesics in the management of pain after orthodontic separator placement: A randomized clinical trial.

Journal of pharmacy & bioallied sciences·2014

Same author

Correction of class III malocclusion using modified tandem appliance-two case reports.

Journal of the Indian Society of Pedodontics and Preventive Dentistry·2013

Same author

Smear Layer Evaluation on Root Canal Preparation with Manual and Rotary Techniques using EDTA as an Irrigant: A Scanning Electron Microscopy Study.

Journal of international oral health : JIOH·2013

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 Video

Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Efficient mapping of backpropagation algorithm onto a network of workstations.

V Sudhakar¹, C Siva Ram Murthy

¹Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society

|February 8, 2008

Summary

This study introduces an efficient method for parallelizing backpropagation (BP) algorithms on networks of workstations (NOWs). The technique achieves better speedups by optimizing communication and weight computation for neural network training.

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Related Experiment Videos

Last Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Area of Science:

Computer Science
Artificial Intelligence
Parallel Computing

Background:

Multilayered neural networks are computationally intensive to train.
Efficient parallelization techniques are crucial for accelerating neural network training.
Existing methods for mapping backpropagation (BP) algorithms to distributed systems have limitations.

Purpose of the Study:

To present an efficient technique for mapping the BP learning algorithm onto a network of workstations (NOWs).
To develop a fully distributed version of the BP algorithm and analyze its speedup.
To compare the proposed method's performance against existing vertical partitioning approaches.

Main Methods:

Adopting a vertical partitioning scheme, dividing each neural network layer into partitions.
Mapping each partition onto an independent workstation in a network of p workstations.
Implementing a fully distributed BP algorithm and conducting speedup analysis.

Main Results:

Achieved better speedups on SUN 3/50 NOWs compared to previous work.
Demonstrated improved performance by utilizing only two communication sets.
Showcased enhanced efficiency by avoiding redundancy in weight computation during training cycles.

Conclusions:

The proposed vertical partitioning technique offers an efficient method for parallelizing BP algorithms on NOWs.
Optimized communication and computation reduce training time for neural networks.
This approach provides a viable solution for accelerating deep learning model training on distributed systems.