Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Synthetic Biology

Synthetic Biology

Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

MindGrab: A spectrally-motivated architecture for accessible deep learning in neuroimaging.

NeuroImage·2026

Same author

Deep learning interpretability in neuroimaging: A comprehensive survey and methodological recommendations.

Imaging neuroscience (Cambridge, Mass.)·2026

Same author

Combining fast and slow fMRI sampling rates can enhance predictive power in resting-state data.

NeuroImage·2025

Same author

Interpretable Disorder Signatures: Probing Neural Latent Spaces for Schizophrenia, Alzheimer's, and Autism Stratification.

Brain sciences·2025

Same author

st-DenseViT: A Weakly Supervised Spatiotemporal Vision Transformer for Dense Prediction of Dynamic Brain Networks.

Human brain mapping·2025

Same author

Using an ordinary differential equation model to separate rest and task signals in fMRI.

Nature communications·2025

Search research articles

相关实验视频

Updated: May 6, 2026

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

缩放合成大脑数据生成的规模

Mike Doan, Sergey Plis

IEEE journal of biomedical and health informatics

|March 3, 2025

概括

此摘要是机器生成的。

线头加速神经成像的深度学习,通过实现高效的,即时合成数据生成. 这种新的管道大大减少了模型训练时间,从几天到几个小时,通过并行数据创建.

更多相关视频

Robust and Highly Reproducible Generation of Cortical Brain Organoids for Modelling Brain Neuronal Senescence In Vitro

Robust and Highly Reproducible Generation of Cortical Brain Organoids for Modelling Brain Neuronal Senescence In Vitro

Published on: May 5, 2022

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

相关实验视频

Last Updated: May 6, 2026

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

Robust and Highly Reproducible Generation of Cortical Brain Organoids for Modelling Brain Neuronal Senescence In Vitro

Robust and Highly Reproducible Generation of Cortical Brain Organoids for Modelling Brain Neuronal Senescence In Vitro

Published on: May 5, 2022

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

科学领域:

神经成像是一种神经成像.
人工智能的人工智能
计算神经科学是一种神经科学.

背景情况:

有限的高质量数据集阻碍了神经成像中的深度学习.
在飞行中合成数据生成是计算密集的.
预先生成的数据不灵活,并导致高存储成本.

研究的目的:

介绍Wirehead,一个可扩展的内存管道,用于高效的即时合成数据生成.
提高性能,减少神经成像中深度学习的计算需求.
在现场解决数据可用性和存储挑战.

主要方法:

开发了一个可扩展的内存数据管道 (Wirehead).
使用并行流程与培训脱的数据生成.
使用MongoDB来有效处理大型数据集.
用SynthSeg评估Wirehead用于合成大脑细分数据生成.

主要成果:

与并行发电机实现了近线性性能增长.
通过16个发电机表现出15.7倍的吞吐量增加.
用20个发电机将模型培训时间从7天缩短到9小时.
成功处理了千兆字节的数据,最大限度地降低了存储成本.

结论:

线头显著加速神经成像中的深度学习实验周期.
管道提供了一个灵活,模块化和耐故障的解决方案.
通过分布式深度学习,实现更雄心勃勃的神经成像研究.