当前位置: 首页 >> 学院公告

薛业翔博士学术报告会

作者        发布时间 2016-12-25      点击量 464

江苏省网络监控工程中心特邀美国康奈尔大学薛业翔博士来校做学术交流。

报告题目:Combining Learning and Reasoning for Decision Making: Integrating Concepts from AI, Economics, Crowd-sourcing, and Sustainability

报告时间:2016年12月28日上午10:40-11:50

报告地点:计算机与软件学院308会议室

报告人:薛业翔 博士

摘要: Systems for decision-making under uncertainty generally require a tight integration of learning and reasoning techniques. In my research, I'm interested in developing strategies for such an integration in the context of a range of applications in computational sustainability. As the first example, I will discuss a game theoretic application which leverages incentives to alleviate the data collection bias from citizen science projects. Citizen science projects have been very successful at collecting rich datasets across different domains. However, the data collected by the citizen scientists are often biased, aligned more directly with the participants’ preferences rather than scientific objectives. We introduce a general methodology to improve the scientific quality of the data collected. Our approach uses incentives to shift the interests of citizen scientists to be more aligned with the goal of obtaining unbiased samples from the field, thus improving the quality of the data collected. We formulate the problem as a two-stage game, which requires an integration of learning, to obtain the parameters that govern the individual behavior of the citizen scientists (the agents), with reasoning, to search for an optimal incentive allocation to achieve the goal of the organizer of the citizen science program. We apply our methodology to eBird, a well-established citizen science program of the Cornell Lab of Ornithology for the collection of bird observations, as a gamified web application, called Avicaching. Our field results show that our Avicaching incentives are remarkably effective at steering the bird watchers' efforts to explore under-sampled areas and hence alleviate the data bias problem in eBird. As a second example, I will present a novel algorithm to solve the Marginal Maximum-A-Posteriori (Marginal MAP) problem, which arises in many applications at the intersection of decision-making and machine learning. Marginal MAP problems unify the two main classes of inference, namely maximization (optimization) and marginal inference (counting), and are believed to have higher complexity than both of them. We propose XOR_MMAP, a novel approach to solve the Marginal MAP problem, which represents the intractable counting subproblem with queries to NP oracles, subject to additional parity constraints. XOR_MMAP provides a constant factor approximation to the Marginal MAP problem, by encoding it as a single optimization in polynomial size of the original problem. We evaluate our approach in several machine learning and decision-making applications, and show that our approach outperforms several state-of-the-art Marginal MAP solvers.

个人简介:薛业翔,现为美国康奈尔大学博士研究生,师从Bart Selman教授和Carla P. Gomes教授。他的研究主要关注自动推理和机器学习方法在智能系统中的有机集成和在统计过程中的应用。他提出的人工智能方法在再生能源、材料科学、众包、公民科学、生态学和计量经济学等众多领域中均有广泛应用。近年来,他特别关注于人工智能方法在新兴的可持续计算领域的研究。薛业翔是全球著名公民科学项目eBird的主要研究和贡献者,这一项目在全球有数十万的志愿者并收集了上百万小时的鸟类观测数据。此外,他在知识表示、推理、学习等人工智能核心领域均有突出贡献。

 

江苏省网络监控工程中心

2016年12月22日

Copyright © 2011 南京信息工程大学 计算机与软件学院. All Rights Reserved.
多火工作室技术支持

建议分辨率 1280*1024