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

Long-term Potentiation

Long-term Potentiation

Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.

Exercise and Muscle Performance

Exercise and Muscle Performance

Exercise induces a range of adaptations in muscle tissue, depending on the type and duration of activity. Such physical training can be broadly categorized into two types: endurance exercises and resistance exercises.
Endurance exercises
Endurance exercises involve running, swimming, or cycling, which require repetitive movements with low force output. When a person engages in endurance exercise, a few noticeable changes occur in their skeletal muscles. For instance, the number of capillaries...

You might also read

Related Articles

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

Sort by

Same author

Oligodendrocyte prosaposin restores subarachnoid haemorrhage-induced consciousness impairment.

Experimental & molecular medicine·2026

Same author

Towards the construction of a virtual yeast.

Nature·2026

Same author

OpenIO: An open framework for AI-native immunotherapy.

Cancer cell·2026

Same author

PFN1 inhibits lytic replication of Kaposi sarcoma-associated herpesvirus through SQSTM1/p62-mediated selective autophagy targeting the KSHV helicase.

Autophagy·2026

Same author

FTO-mediated m6A demethylation of BCLW mRNA attenuates neuronal ferroptosis after intracerebral hemorrhage.

Experimental neurology·2026

Same author

CRA5 a high-fidelity compressed reanalysis atmospheric dataset for weather and climate research.

Scientific data·2026

Search research articles

Related Experiment Video

Updated: May 15, 2025

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

Stimulative Training++: Go Beyond the Performance Limits of Residual Networks.

Peng Ye, Tong He, Shengji Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence

|April 7, 2025

Summary

Residual networks suffer from "network loafing," where subnetworks underperform. Stimulative training boosts performance by encouraging subnetworks to work harder, improving deep learning models.

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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 15, 2025

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Deep Learning
Computer Vision
Artificial Intelligence

Background:

Residual networks are crucial in deep learning.
They can be viewed as ensembles of shallow subnetworks.
Subnetworks may underperform when part of a larger network, a phenomenon termed 'network loafing'.

Purpose of the Study:

To investigate network loafing in residual networks.
To propose a novel training scheme, stimulative training, to mitigate network loafing.
To enhance the performance of residual networks beyond current limits.

Main Methods:

Introduced 'network loafing' as a problem where subnetworks exert less effort.
Proposed 'stimulative training,' a scheme using KL divergence loss for subnetwork supervision.
Developed three strategies: KL- loss for logit direction, random smaller inputs, and inter-stage sampling rules.

Main Results:

Stimulative training boosted ResNet50 on ImageNet to 80.5% Top1 accuracy without additional data or model changes.
With uniform augmentation, accuracy reached 81.0% Top1, surpassing existing benchmarks.
Effectiveness was verified across various models, datasets, and tasks.

Conclusions:

Stimulative training effectively addresses network loafing in residual networks.
The proposed method offers significant performance gains with minimal modifications.
Advocated as a general, next-generation training technology for residual networks.