Explainable Deep Learning for Temporal Situational Understanding

用于时间情境理解的可解释深度学习

• 批准号: 2123459
• 金额: --
• 依托单位: CARDIFF UNIVERSITY
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2018
• 资助国家: 英国
• 起止时间: 2018 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2123459
• 关键词: Explainable; Deep; Learning; Temporal; Situational

Huge advances have been made in machine learning in recent years due to breakthroughs in deep neural networks, called Deep Learning (DL). However, a key problem with DL approaches is that they are generally seen as being "black boxes": while they may work well in particular applications, it is usually unclear how they work, leading to challenges in improving their performance when they fail, and issues of user trust. There is consequently great interest in researching techniques to improve the interpretability of DL approaches to allow DL systems to generate explanations of how they reached a decision. To be useful, such explanations need to be generated in human-understandable terms, for example, identifying image features that were significant in a classification decision, or providing a brief textual description. They should also allow a human to take appropriate action upon receipt of the explanation; for example, satisfying transparency requirements for accountable decision-making or, in the event of a misclassification providing useful information on how to improve future performance of the DL system. The goal of this PhD is to make progress in this challenging area of DL, with a particular focus on situational understanding problems where the DL system is intended to assist a human decision maker in domains such as emergency response, security and policing.Situational understanding requires three key elements in terms of machine learning, both of which need to be explainable: (1) learning of temporal relationships, including predictions of likely future states (i.e., based on the current situation, what is likely to happen next); (2) learning at multiple hierarchical scales, from detection of low-level objects to identification of high-level relationships; and (3) learning from the fusion of multiple data streams of different modalities (e.g., imagery, text, GPS, etc). As an example, consider the problem of managing a large-scale event in a city centre, where streams of CCTV imagery, social media text, and real-time location data may be used to predict potential overcrowding and consequential disruption. This objective of this PhD will be to focus in particular on (1) - explainability of learned temporal relationships.This PhD will be carried out within the Distributed Analytics and Information Sciences International Technology Alliance (DAIS ITA), a collaboration between Cardiff University, IBM, Airbus, BAE Systems, University College London, University of California Los Angeles, and other UK and US partners - see https://dais-ita.org/ At Cardiff University the PhD will be supervised by members of the Crime and Security Research Institute, the School of Computer Science and Informatics, and the School of Engineering's Sensors, Signals and Imaging Group.

近年来，由于深度神经网络（称为深度学习（DL））的突破，机器学习取得了巨大的进步。然而，DL方法的一个关键问题是它们通常被视为“黑盒子”：虽然它们在特定应用程序中可能工作良好，但通常不清楚它们是如何工作的，这导致在它们失败时提高性能的挑战以及用户信任问题。因此，有很大的兴趣在研究技术，以提高DL方法的可解释性，让DL系统生成的解释，他们如何达成的决定。为了有用，这些解释需要以人类可理解的术语生成，例如，识别在分类决策中重要的图像特征，或提供简短的文本描述。它们还应该允许人类在收到解释后采取适当的行动;例如，满足负责决策的透明度要求，或者在错误分类的情况下提供有关如何改善DL系统未来性能的有用信息。这个博士学位的目标是在DL这一具有挑战性的领域取得进展，特别关注DL系统旨在帮助人类决策者在应急响应，安全和警务等领域的情景理解问题。情景理解需要机器学习方面的三个关键要素，这两个要素都需要解释：（1）时间关系的学习，包括可能的未来状态的预测（即，基于当前情况，接下来可能发生什么）;（2）在多个分级尺度上学习，从低级对象的检测到高级关系的识别;以及（3）从不同模态的多个数据流的融合中学习（例如，图像、文本、GPS等）。例如，考虑管理市中心大型活动的问题，其中闭路电视图像流、社交媒体文本和实时位置数据可用于预测潜在的过度拥挤和相应的中断。该博士学位的目标将特别关注（1）-学习时间关系的可解释性。该博士学位将在分布式分析和信息科学国际技术联盟（DAIS ITA）内进行，该联盟是卡迪夫大学，IBM，空中客车公司，BAE系统公司，伦敦大学学院，加州大学洛杉矶分校以及其他英国和美国合作伙伴之间的合作-见https://dais-ita.org/大学的博士将由犯罪和安全研究所，计算机科学和信息学院，以及工程学院的传感器，信号和成像组的成员监督。