Theory and Practice of Un-trained Neural Networks

未经训练的神经网络的理论与实践

• 批准号: 456465471
• 负责人: Professor Dr. Reinhard Heckel
• 金额: --
• 依托单位: Professur für Machine Learning
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/456465471?language=en
• 关键词: Theory; Practice; Un; trained; Neural

Deep neural networks have emerged as highly successful tools for signal and image recovery and restoration. This success is often attributed to large amounts of training data. However, recent findings challenge this view and instead suggest that a major contributing factor to this success is that the architecture of the network imposes strong prior assumptions---so strong that it enables image recovery without any training data. For example, our promising preliminary results show that it is possible i) to remove noise and corruptions from an image by fitting a convolutional network to the corrupted image, without ever having trained the network, and to ii) achieve state-of-the-art performance for accelerated magnetic resonance imaging, an important medical imaging technique, again without using any training data.However, it is widely open why un-trained networks work so well for signal recovery problems, how their high computational cost can be reduced, and whether this technique is applicable to a much broader set of problems, beyond image reconstruction problems. Motivated by the recent success of un-trained neural networks, the goal of this project is to i) understand theoretically why un-trained neural networks work so well for imaging problems, ii) evaluate and guarantee robustness of un-trained neural networks,iii) develop fast algorithms for signal recovery with un-trained methods, andiv) to build new algorithms based on un-trained neural networks for applications beyond imaging, in particular for unsupervised learning.

深度神经网络已经成为信号和图像恢复和恢复的非常成功的工具。这种成功通常归功于大量的训练数据。然而，最近的研究结果挑战了这一观点，相反，这一成功的一个主要因素是网络的架构强加了强有力的先验假设-如此强大，以至于它可以在没有任何训练数据的情况下进行图像恢复。例如，我们有希望的初步结果表明，有可能i）通过将卷积网络拟合到受损图像来从图像中去除噪声和受损，而无需训练网络，以及ii）再次在不使用任何训练数据的情况下实现加速磁共振成像（一种重要的医学成像技术）的最先进性能。为什么未经训练的网络对于信号恢复问题工作得如此好，如何能够降低它们的高计算成本，以及这种技术是否适用于图像重建问题之外的更广泛的问题集合，这些都是广泛公开的。受未训练神经网络最近成功的启发，该项目的目标是i）从理论上理解为什么未训练神经网络在成像问题上如此有效，ii）评估和保证未训练神经网络的鲁棒性，iii）使用未训练方法开发信号恢复的快速算法，以及iv）构建基于未训练神经网络的新算法，用于成像以外的应用，特别是对于无监督学习。