RI: AF: Small: Deep Learning Theory

RI：AF：小：深度学习理论

• 批准号: 1619362
• 负责人: Peter Bartlett
• 金额: $ 49万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-07-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1619362&HistoricalAwards=false
• 关键词: RI; AF; Small; Deep; Learning

Deep learning has recently emerged as a major advance in machine learning and AI. This technology for learning from data has provided field-changing performance improvements in image classification and speech recognition, it has displayed impressive performance across a large variety of areas (including natural language processing, robotics, audio processing, and computational chemistry), and it has become a central ingredient in AI systems. But despite these successes, our understanding of these methods is incomplete. The broad goal of this research project is to address this grand challenge: to develop analysis techniques that enable us to understand when and why deep learning methods will be successful, and to design effective methods with explicit performance guarantees. Successful research outcomes have a significant potential for practical impact in the large and growing set of application areas where these methods are used.The project aims to understand the performance of deep learning methods - in particular to elucidate what aspects are essential for their success - and hence to develop principled design techniques and performance guarantees. The objectives are: to characterize the performance impacts of the critical features of current neural network architectures: scale, depth, nonlinearities, and regularization; to develop analysis techniques that facilitate our understanding of the approximation and estimation properties of deep architectures; to identify the boundary between easy and hard learning problems for deep networks; and to develop methods with explicit performance guarantees for optimization in deep neural networks. Successful research outcomes are likely to increase our understanding of deep learning methods, to provide performance guarantees for these methods, and to facilitate the principled design of novel deep learning methods.

深度学习最近成为机器学习和人工智能的重大进步。 这种从数据中学习的技术在图像分类和语音识别方面提供了改变领域的性能改进，它在许多领域（包括自然语言处理、机器人、音频处理和计算化学）都表现出了令人印象深刻的性能，并且它已经成为人工智能系统的核心组成部分。 但尽管取得了这些成功，我们对这些方法的理解仍然不完整。该研究项目的总体目标是应对这一巨大挑战：开发分析技术，使我们能够了解深度学习方法何时以及为何会成功，并设计具有明确性能保证的有效方法。 成功的研究成果对于使用这些方法的大量且不断增长的应用领域具有巨大的实际影响潜力。该项目旨在了解深度学习方法的性能 - 特别是阐明哪些方面对其成功至关重要 - 以及因此开发原则性的设计技术和性能保证。 目标是： 描述当前神经网络架构的关键特征对性能的影响：规模、深度、非线性和正则化；开发分析技术，促进我们理解深层架构的近似和估计特性；确定深度网络的简单学习问题和困难学习问题之间的界限；并开发具有明确性能保证的方法来优化深度神经网络。 成功的研究成果可能会增加我们对深度学习方法的理解，为这些方法提供性能保证，并促进新型深度学习方法的原则设计。