Recurrent Deep Learning Machines

循环深度学习机

• 批准号: 1028048
• 负责人: James Lo
• 金额: $ 29.52万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-09-01 至 2014-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1028048&HistoricalAwards=false
• 关键词: Recurrent; Deep; Learning; Machines

The objective of this research is to develop a new paradigm of deep learning machine - those with a feedback structure. Feedbacks bring to computing nodes current or past information contained in neighboring or larger receptive fields of other computing nodes from the same or higher layers for forming better local representations or features. Such information is required for processing dynamical data and for maximizing generalization capabilities on static data. The approach of this research is to select or design deep and recurrent architectures, develop generative and discriminative learning techniques, and integrating the risk-averting method of convexifying training criteria into training recurrent deep learning machines. Intellectual Merit: Recurrent neural networks are irreplaceable for applications involving dynamical data and are fundamentally better than feedforward networks even on static data. However, difficulty in training recurrent networks has stifled development and understanding of them. The proposed research is expected to help remove this difficulty, bring forth the full power of recurrent neural networks, and boost interests in neural networks in general, which have unfortunately and undeservedly fallen out of favor in recent years. Broader Impact: Recurrent deep learning machines are powerful for static and dynamical classification and regression, including image and video recognition, analysis and compression; nonlinear system identification/control; signal processing/filtering; and critical system health/fault monitoring/detection. Therefore, the proposed work will contribute greatly to medical instrumentation, computer/robot/information technology, wireless telecommunication, national defense, and homeland security. Recurrent deep learning machines will ecome an important component in the graduate education in engineering and computer science

这项研究的目标是开发一种新的深度学习机器范例——具有反馈结构的机器。反馈将来自相同或更高层的其他计算节点的相邻或更大感受野中包含的当前或过去信息带到计算节点，以形成更好的局部表示或特征。处理动态数据和最大化静态数据的泛化能力需要此类信息。这项研究的方法是选择或设计深度和循环架构，开发生成和判别式学习技术，并将凸化训练标准的风险规避方法集成到训练循环深度学习机器中。 智力优点：循环神经网络对于涉及动态数据的应用是不可替代的，并且即使在静态数据上也从根本上优于前馈网络。然而，训练循环网络的困难阻碍了它们的发展和理解。拟议的研究预计将有助于消除这一困难，发挥循环神经网络的全部力量，并提高人们对神经网络的整体兴趣，不幸的是，神经网络近年来已不受欢迎。 更广泛的影响：循环深度学习机对于静态和动态分类和回归功能强大，包括图像和视频识别、分析和压缩；非线性系统识别/控制；信号处理/滤波；以及关键系统健康/故障监控/检测。因此，拟议的工作将对医疗仪器、计算机/机器人/信息技术、无线电信、国防和国土安全做出巨大贡献。循环深度学习机将成为工程和计算机科学研究生教育的重要组成部分