Learn From The Best: training AI using biological expert attention

向最优秀的人学习:利用生物专家的注意力训练人工智能

基本信息

  • 批准号:
    BB/T012129/1
  • 负责人:
  • 金额:
    $ 17.82万
  • 依托单位:
  • 依托单位国家:
    英国
  • 项目类别:
    Research Grant
  • 财政年份:
    2020
  • 资助国家:
    英国
  • 起止时间:
    2020 至 无数据
  • 项目状态:
    已结题

项目摘要

Artificial intelligence (AI) is having a massive impact on many disciplines, including biological science. Its power is impressive and its adoption will change the nature of research, but at the moment the way it is developed has severe practical limitations. Despite the recent developments in machine learning and AI, humans still possess an unrivalled ability to just look at a picture, and understand exactly what is going on. A human expert is able to look at a picture of a plant with disease symptoms, for example, and immediately quantify the severity of the infection. AI promises to revolutionise bioimage analysis, but as of today an expert human will outperform an AI given only a small set of images to learn from.One important difference between humans and modern AI is the way we are taught to perform a task. A human will learn which parts of an image are important, then scan the images to find these areas before coming to reach a scoring decision. AI is typically trained using labeled data, where only the output label matters. An AI does not know which parts of the image are important, or where it should look. This often leads to poor performance when the task is challenging, or when only small datasets are available. To achieve the impressive results as has been documented in the news, current AI must use very laborious and inefficient training processes, which are often impractical in a real world scientific setting.This project will develop a new, smarter way to train artificial intelligence methods, using similar mechanisms to how human experts make decisions. To do this, our AI will study how human experts approach the same problems by using gaze tracking to see where an expert looked, and when. The result will be AI methods that learn to look in the right places, and so are able to take more difficult scoring decisions with less training data than they would previously need. Put simply, we believe that an AI that is able to look in the correct places before making a decision will be more effective than one that attempts to simply make a decision without knowing where to look.In this project we will first develop the hardware and software approaches necessary to capture expert human gaze during image scoring. This raw gaze information will be processed using novel algorithms, and fed into a new deep learning AI system along with the labelled scores, guiding it towards more informed decision making. The AI will examine where in the images human experts looked when providing an image label, and will learn to look in those same places when it replicates the same task. This is a new approach to training AI. Finally, we will build a new type of deep neural network AI system that can be guided by this additional information, knowing where to look, and what to do.We will demonstrate this work on important datasets of plant disease, but we also believe this approach will massively reduce the time required to annotate datasets across all fields of life and biomedical science, and at the same time produce even more impressive and accurate AI results. This could represent a step-change in the adoption and ease of use of AI tools in the world of bioscience, allowing for more efficient training on smaller image datasets.
人工智能(AI)正在对包括生物科学在内的许多学科产生巨大影响。它的力量令人印象深刻,它的采用将改变研究的性质,但目前它的开发方式具有严重的实际局限性。尽管机器学习和人工智能最近取得了发展,但人类仍然拥有无与伦比的能力,只需查看图片即可准确理解正在发生的事情。例如,人类专家能够查看具有疾病症状的植物的图片,并立即量化感染的严重程度。人工智能有望彻底改变生物图像分析,但截至目前,仅需要一小部分图像可供学习,专家人类的表现就会优于人工智能。人类和现代人工智能之间的一个重要区别是我们被教导执行任务的方式。人类将了解图像的哪些部分是重要的,然后扫描图像以找到这些区域,然后做出评分决定。人工智能通常使用标记数据进行训练,其中只有输出标签很重要。人工智能不知道图像的哪些部分重要,或者应该看哪里。当任务具有挑战性或只有小数据集可用时,这通常会导致性能不佳。为了实现新闻中记载的令人印象深刻的结果,当前的人工智能必须使用非常费力且低效的训练过程,这在现实世界的科学环境中通常是不切实际的。该项目将开发一种新的、更智能的方法来训练人工智能方法,使用与人类专家做出决策类似的机制。为此,我们的人工智能将研究人类专家如何解决相同的问题,通过使用视线跟踪来查看专家的视线和时间。结果将是人工智能方法学会寻找正确的位置,因此能够用比以前需要的更少的训练数据做出更困难的评分决策。简而言之,我们相信,能够在做出决定之前查看正确位置的人工智能,会比在不知道该查看哪里的情况下尝试简单地做出决定的人工智能更有效。在这个项目中,我们将首先开发硬件和在图像评分过程中捕获专家人类凝视所需的软件方法。这些原始注视信息将使用新颖的算法进行处理,并与标记的分数一起输入新的深度学习人工智能系统,引导其做出更明智的决策。人工智能将在提供图像标签时检查人类专家在图像中查看的位置,并在复制相同任务时学习查看这些相同的位置。这是一种训练人工智能的新方法。最后,我们将构建一种新型的深度神经网络人工智能系统,该系统可以通过这些附加信息来指导,知道该往哪里看,以及做什么。我们将在植物病害的重要数据集上演示这项工作,但我们也相信这一点该方法将大大减少生命和生物医学科学所有领域的数据集注释所需的时间,同时产生更令人印象深刻和更准确的人工智能结果。这可能代表生物科学领域人工智能工具的采用和易用性发生了巨大变化,从而可以对较小的图像数据集进行更有效的训练。

项目成果

期刊论文数量(1)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies
  • DOI:
    10.1016/j.cviu.2023.103776
  • 发表时间:
    2021-11
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Bowen Deng;A. French;Michael P. Pound
  • 通讯作者:
    Bowen Deng;A. French;Michael P. Pound
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Michael Pound其他文献

Application of RESNET50 Convolution Neural Network for the Extraction of Optical Parameters in Scattering Media
RESNET50卷积神经网络在散射介质光学参数提取中的应用
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Bowen Deng;Yihan Zhang;Andrew Parkes;Alexander Bentley;Amanda J. Wright;Michael Pound;Michael Somekh
  • 通讯作者:
    Michael Somekh

Michael Pound的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Michael Pound', 18)}}的其他基金

Digging Deeper with AI: Canada-UK-US Partnership for Next-generation Plant Root Anatomy Segmentation
利用人工智能进行更深入的挖掘:加拿大、英国、美国合作开发下一代植物根部解剖分割
  • 批准号:
    BB/Y513908/1
  • 财政年份:
    2024
  • 资助金额:
    $ 17.82万
  • 项目类别:
    Research Grant
LeMuR: Plant Root Phenotyping via Learned Multi-resolution Image Segmentation
LeMuR:通过学习的多分辨率图像分割进行植物根表型分析
  • 批准号:
    BB/P026834/1
  • 财政年份:
    2017
  • 资助金额:
    $ 17.82万
  • 项目类别:
    Research Grant

相似国自然基金

BEST4作为Notch2-Hes4轴的关键靶分子通过拮抗STAT3二聚化逆转EMT抑制结直肠癌转移的作用和机制研究
  • 批准号:
  • 批准年份:
    2021
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
Best1通道在脑缺血急性损伤和功能修复中的特殊双相作用
  • 批准号:
    82171293
  • 批准年份:
    2021
  • 资助金额:
    54 万元
  • 项目类别:
    面上项目
中国医患治疗偏好研究:基于Best-worst标度法的探索
  • 批准号:
    71804122
  • 批准年份:
    2018
  • 资助金额:
    18.0 万元
  • 项目类别:
    青年科学基金项目
基于学术大数据的科研合作者推荐问题研究——推荐最合适的而不是最好的
  • 批准号:
    61662068
  • 批准年份:
    2016
  • 资助金额:
    41.0 万元
  • 项目类别:
    地区科学基金项目
新发现的Bestrophin 3 激活剂降压机制的研究
  • 批准号:
    81070215
  • 批准年份:
    2010
  • 资助金额:
    33.0 万元
  • 项目类别:
    面上项目

相似海外基金

REU Site: Interdisciplinary Biological Engineering and Science Training (I-BEST)
REU 网站:跨学科生物工程和科学培训 (I-BEST)
  • 批准号:
    2349757
  • 财政年份:
    2024
  • 资助金额:
    $ 17.82万
  • 项目类别:
    Standard Grant
Dental-Biomedical Engineering Scholars Training (D-Best) Program
牙科生物医学工程学者培训(D-Best)计划
  • 批准号:
    10845831
  • 财政年份:
    2023
  • 资助金额:
    $ 17.82万
  • 项目类别:
Building and Implementing Best Practices for Buprenorphine Initiation in the Setting of Fentanyl Use
在芬太尼使用情况下建立和实施丁丙诺啡起始的最佳实践
  • 批准号:
    10721763
  • 财政年份:
    2023
  • 资助金额:
    $ 17.82万
  • 项目类别:
Antibodies to Viral Vectors in Gene Therapy Research: Seeking Best Practices for Sponsor Policies and Communications
基因治疗研究中的病毒载体抗体:寻求赞助商政策和沟通的最佳实践
  • 批准号:
    10683623
  • 财政年份:
    2023
  • 资助金额:
    $ 17.82万
  • 项目类别:
Beginning and Early Stage Translational (BEST) Researchers
初级和早期转化 (BEST) 研究人员
  • 批准号:
    10622203
  • 财政年份:
    2023
  • 资助金额:
    $ 17.82万
  • 项目类别:
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了