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

Related Concept Videos

Step-Growth Polymerization: Overview

Step-Growth Polymerization: Overview

Step-growth or condensation polymerization is a stepwise reaction of bi or multifunctional monomers to form long-chain polymers. As all the monomers are reactive, most of the monomers are consumed at the early stages of the reaction to form small chains of reactive oligomers, which then combine to form long polymer chains in the late stages. Hence, the reaction has to proceed for a long time to achieve high molecular weight polymers.
Many natural and synthetic polymers are produced by...

You might also read

Related Articles

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

Sort by

Same author

Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network.

Chaos (Woodbury, N.Y.)·2025

Same author

A multilayered bidirectional associative memory model for learning nonlinear tasks.

Neural networks : the official journal of the International Neural Network Society·2023

Same author

Embodied working memory during ongoing input streams.

PloS one·2021

Same author

Discrimination of Motion Direction in a Robot Using a Phenomenological Model of Synaptic Plasticity.

Computational intelligence and neuroscience·2019

Same author

Spiking Neurons Integrating Visual Stimuli Orientation and Direction Selectivity in a Robotic Context.

Frontiers in neurorobotics·2018

Same author

Unsupervised Neural Network Quantifies the Cost of Visual Information Processing.

PloS one·2015

Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026

Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026

Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026

Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026

Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026

Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 26, 2025

ODELAY: A Large-scale Method for Multi-parameter Quantification of Yeast Growth

ODELAY: A Large-scale Method for Multi-parameter Quantification of Yeast Growth

Published on: July 3, 2017

Dynamic multilayer growth: Parallel vs. sequential approaches.

Matt Ross¹, Nareg Berberian¹, Albino Nikolla¹

¹Laboratory for- Computational Neurodynamics and Cognition, School of Psychology, University of Ottawa, Ottawa, ON, Canada.

|May 9, 2024

Summary

This summary is machine-generated.

Growing neural networks wider and deeper is key for complex data. This study shows parallel layer growth in deep networks performs as well as or better than sequential growth, optimizing architecture for specific tasks.

More Related Videos

Density Gradient Multilayered Polymerization DGMP: A Novel Technique for Creating Multi-compartment, Customizable Scaffolds for Tissue Engineering

Density Gradient Multilayered Polymerization DGMP: A Novel Technique for Creating Multi-compartment, Customizable Scaffolds for Tissue Engineering

Published on: February 12, 2013

A Multilayer Microfluidic Platform for the Conduction of Prolonged Cell-Free Gene Expression

A Multilayer Microfluidic Platform for the Conduction of Prolonged Cell-Free Gene Expression

Published on: October 6, 2019

Related Experiment Videos

Last Updated: Jun 26, 2025

ODELAY: A Large-scale Method for Multi-parameter Quantification of Yeast Growth

ODELAY: A Large-scale Method for Multi-parameter Quantification of Yeast Growth

Published on: July 3, 2017

Density Gradient Multilayered Polymerization DGMP: A Novel Technique for Creating Multi-compartment, Customizable Scaffolds for Tissue Engineering

Density Gradient Multilayered Polymerization DGMP: A Novel Technique for Creating Multi-compartment, Customizable Scaffolds for Tissue Engineering

Published on: February 12, 2013

A Multilayer Microfluidic Platform for the Conduction of Prolonged Cell-Free Gene Expression

A Multilayer Microfluidic Platform for the Conduction of Prolonged Cell-Free Gene Expression

Published on: October 6, 2019

Area of Science:

Artificial Intelligence
Machine Learning
Deep Learning

Background:

Determining when to add hidden units or layers is crucial for constructive algorithms, especially in deep networks.
Growing network width and depth enhances information capture and modeling of complex data representations.

Purpose of the Study:

To investigate the effects of sequential versus parallel hidden layer growth in multilayer neural networks.
To compare the performance of parallel growth with sequential methods, including Dynamic Node Creation.

Main Methods:

A population dynamics-inspired growing algorithm was modified for parallel growth in multilayer perceptrons.
Sequential and parallel growth strategies were compared on benchmark classification tasks using a three-hidden-layer network.
Variants explored different hidden layer initializations and weight update methods.

Main Results:

Parallel hidden layer growth achieved performance comparable to or exceeding sequential approaches.
Parallel growth favored the development of narrower, deep architectures optimized for specific tasks.
The population dynamics-inspired approach demonstrated potential for both sequential and parallel growth of deep networks.

Conclusions:

Parallel growth is a viable and effective strategy for constructing deep neural networks.
Optimizing network architecture through parallel growth can lead to task-specific, efficient models.
Dynamic growth algorithms offer flexibility in managing network complexity for deep learning applications.