Constrained Neural Networks
约束神经网络
基本信息
- 批准号:448537382
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:德国
- 项目类别:Research Grants
- 财政年份:
- 资助国家:德国
- 起止时间:
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
The training of deep artificial neural networks has led to major breakthroughs in the automatic processing and analysis of image data within the last decade. Unfortunately, the significant expressive power of such approaches, currently comes at the price of lacking control: Even if a network has been trained to solve a specific task on millions of training examples, there are rarely any mechanisms to provably guarantee that its output follows a given (physical) data formation process, which can explicitly be stated as a (parametric) mathematical constraint. This lack of control is a severe problem due to two reasons,1. It ultimately limits the applicability of learning-based approaches in some safety-critical applications where constraints need to be satisfied, and2. it prevents the inclusion of prior knowledge to guide machine learning based techniques and reduce the amount of training data required to train faithful models. Therefore, the goal of this project is to study fundamental methodologies for provably constraining the output of neural networks to a predefined (parameterized) set. It builds upon the method of energy dissipating networks developed by the applicant that allows to iteratively minimize any smooth energy with a neural network by projecting onto the set of descent directions in its final layer. The technical goal of this proposal is to exploit the idea of energy dissipating networks to provably enforce constraints, e.g. by using the squared distance to the constraint set as an energy. Specific foci will be put on structured as well as non-convex constraint sets. Finally, effectiveness of constrained networks will be tested and verified in the applications of weakly supervised segmentation with shape prior constraints as well as graph matching problems.
深度人工神经网络的训练在过去十年中导致了图像数据自动处理和分析的重大突破。不幸的是,这些方法的显著表现力目前是以缺乏控制为代价的:即使一个网络已经被训练来解决数百万个训练示例的特定任务,也很少有任何机制可以证明其输出遵循给定的(物理)数据形成过程,这可以明确地表示为(参数)数学约束。这种缺乏控制是一个严重的问题,由于两个原因,1。它最终限制了基于学习的方法在一些需要满足约束的安全关键应用中的适用性。它防止了包含先验知识来指导基于机器学习的技术,并减少了训练忠实模型所需的训练数据量。 因此,本项目的目标是研究可证明地将神经网络的输出约束到预定义(参数化)集合的基本方法。它建立在由申请人开发的能量耗散网络的方法之上,该方法允许通过投影到其最终层中的下降方向集合上来迭代地最小化具有神经网络的任何平滑能量。该提案的技术目标是利用能量耗散网络的思想来可证明地强制约束,例如通过使用到约束集的平方距离作为能量。具体重点将放在结构化以及非凸约束集。最后,将在具有形状先验约束的弱监督分割以及图匹配问题的应用中测试和验证约束网络的有效性。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Professor Dr. Michael Möller其他文献
Professor Dr. Michael Möller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('Professor Dr. Michael Möller', 18)}}的其他基金
L2S-Training with Continuous Sensor System Parameters and Irregular Data
使用连续传感器系统参数和不规则数据进行 L2S 训练
- 批准号:
498556346 - 财政年份:
- 资助金额:
-- - 项目类别:
Research Units
相似国自然基金
Neural Process模型的多样化高保真技术研究
- 批准号:62306326
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
相似海外基金
EAGER: Search-Accelerated Markov Chain Monte Carlo Algorithms for Bayesian Neural Networks and Trillion-Dimensional Problems
EAGER:贝叶斯神经网络和万亿维问题的搜索加速马尔可夫链蒙特卡罗算法
- 批准号:
2404989 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333881 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333882 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks
DMS-EPSRC:机器学习中在线训练算法的渐近分析:循环、图形和深度神经网络
- 批准号:
EP/Y029089/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
SkyANN: Skyrmionic Artificial Neural Networks
SkyANN:Skyrmionic 人工神经网络
- 批准号:
10108371 - 财政年份:2024
- 资助金额:
-- - 项目类别:
EU-Funded
CAREER: Rethinking Spiking Neural Networks from a Dynamical System Perspective
职业:从动态系统的角度重新思考尖峰神经网络
- 批准号:
2337646 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Continuing Grant
RII Track-4:@NASA: Automating Character Extraction for Taxonomic Species Descriptions Using Neural Networks, Transformer, and Computer Vision Signal Processing Architectures
RII Track-4:@NASA:使用神经网络、变压器和计算机视觉信号处理架构自动提取分类物种描述的字符
- 批准号:
2327168 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
Neural Networks for Stationary and Evolutionary Variational Problems
用于稳态和进化变分问题的神经网络
- 批准号:
2424801 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Continuing Grant
Approximation theory of structured neural networks
结构化神经网络的逼近理论
- 批准号:
DP240101919 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Discovery Projects