RI: Synergistic Machine Learning: Collaboration and Topology Exploitation in Dynamic Environments

提案0705681“RI：协作式机器学习：动态环境中的协作和拓扑开发”PI：Terran Lane University of New墨西哥摘要本项目的目标是研究用于网络的新一代机器学习方法，该网络由大量集成了计算、感知和通信的廉价、轻量级、强大的节点组成。这些节点嵌入在物理世界中，将自组装成环境感知网络，以帮助进行环境监控、安全、工作流程、教育和娱乐。为了实现这些目标，这种无处不在的计算网络需要能够将不同的传感器信息流整合到一致的环境视图中。该项目旨在创建新一代机器学习方法，以应对由此带来的数据融合和环境意识挑战。该项目将开发具有拓扑意识的机器学习方法，这些方法(A)学习和利用环境的拓扑结构，(B)使分布式学习代理之间能够进行协作学习。该项目将在目前安装在两座活火山：基拉韦厄(夏威夷)和山上的实时传感器网络上测试这些新的机器学习方法。埃里巴斯(南极洲)。这个项目将通过研究助学金让本科生和研究生参与。此外，这个项目将通过萨利骑车节的中学生工作坊让大学预科学生作为调查人员参与。这项工作寻求通过开辟当前技术之外的新机器学习问题的广阔空间来改变机器学习和泛在计算，并通过启发泛在计算系统的新功能的开发来实现。

Proposal 0705681"RI: Synergistic Machine Learning: Collaboration and Topology Exploitation in Dynamic Environments."PI: Terran LaneUniversity of New MexicoABSTRACTThe goal of this project is to investigate a new generation of machine learning methods for networks comprised of a large number of inexpensive, lightweight, powerful nodes that integrate computation, sensing, and communication. Embedded in the physical world, these nodes will self-assemble into environmentally-aware networks to assist with environmental monitoring, safety, workflows, education, and entertainment. To achieve these goals, such ubiquitous computing networks need to be able to integrate diverse streams of sensor information into coherent views of the environment. This project seeks to create a new generation of machine learning methods to address the resulting data fusion and environmental awareness challenges. The project will develop topology-aware machine learning methods that (a) learn and exploit the topological structure of the environment, and (b) enable collaborative learning among distributed learning agents. This project will test these new machine learning methods on live sensor networks currently installed at two active volcanos: Kilauea (Hawaii) and Mt. Erebus (Antarctica). This project will involve undergraduate and graduate students via research assistantships. Further, this project will involve pre-college students as investigators through middle-school student workshops at the Sally Ride Festival. This work seeks to transform both machine learning and ubiquitous computing by opening up a vast space of novel machine learning problems that are beyond current techniques, and by inspiring development of new capabilities for ubiquitous computing systems.