Machine Learning for Tomorrow: Efficient, Flexible, Robust and Automated

面向未来的机器学习：高效、灵活、稳健和自动化

• 批准号: EP/T005637/1
• 负责人: Richard Turner
• 金额: $ 208.89万
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FT005637%2F1
• 关键词: Machine; Learning; Tomorrow; Efficient; Flexible

Artificial intelligence systems have recently led to significant advances in the state-of-the-art in downstream fields including computer vision, speech and natural language processing, and game playing. Although impressive, these advances mask a set of fundamental limitations of the underlying machine learning technology that need to be addressed to unlock gains in a wide variety of applications relevant to industry and society. These limitations come in four main forms. First current approaches are data-inefficient requiring extremely large and painstakingly curated datasets. Second, they are inflexible solving single tasks that are fixed through time. Third, the current approaches are brittle as performance can degrade catastrophically in the face of noise, missing data or adversarially selected data points. Fourth, the approaches are only semi-automated requiring an expert to design and tune them. These limitations mean that many important application domains are currently out of reach. For example, in medicine we typically have only small and noisy datasets which requires data-efficient and robust machine learning. Providing machine learning as a service requires fully-automated machine learning. This Prosperity Partnership will develop machine learning that is data-efficient, robust, flexible and automated by leveraging recently developed technology from the University of Cambridge's Machine Learning Group and deep expertise from Microsoft Research Cambridge. This partnership has identified a unique testbed of impactful application domains: health, enterprise tools and games development. This research programme is central to realising Microsoft's vision to empower every developer, organization and individual to innovate and transform the world with AI. Moreover, this area of immediate and wide-ranging national importance, and provides pathways to impact by partnering with one of the world's largest technology companies.

人工智能系统最近在下游领域取得了重大进展，包括计算机视觉，语音和自然语言处理以及游戏。尽管这些进步令人印象深刻，但它们掩盖了底层机器学习技术的一系列基本局限性，需要解决这些局限性，才能在与工业和社会相关的各种应用中获得收益。这些限制主要有四种形式。首先，目前的方法是数据效率低下的，需要非常大和精心策划的数据集。其次，他们在解决单一任务时不够灵活，这些任务是随着时间的推移而固定的。第三，目前的方法是脆弱的，因为性能可能会在面对噪声、丢失数据或相反选择的数据点时灾难性地下降。第四，这些方法只是半自动化的，需要专家来设计和调整它们。这些限制意味着许多重要的应用领域目前还无法实现。例如，在医学中，我们通常只有小而嘈杂的数据集，这需要数据高效和强大的机器学习。将机器学习作为服务提供需要全自动化的机器学习。该繁荣合作伙伴关系将利用剑桥大学机器学习小组最近开发的技术和微软研究院剑桥的深厚专业知识，开发数据高效、强大、灵活和自动化的机器学习。该合作伙伴关系确定了一个独特的有影响力的应用领域测试平台：健康，企业工具和游戏开发。这项研究计划是实现微软愿景的核心，即让每个开发人员、组织和个人都能通过人工智能创新和改造世界。此外，这一领域具有直接和广泛的国家重要性，并通过与世界上最大的技术公司之一合作，提供了产生影响的途径。

项目成果

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

• DOI: 10.48550/arxiv.2206.08671
• 发表时间: 2022-06
• 期刊: ArXiv
• 作者: Aliaksandra Shysheya;J. Bronskill;Massimiliano Patacchiola;Sebastian Nowozin;Richard E. Turner

Memory Efficient Meta-Learning with Large Images

• 发表时间: 2021-07
• 作者: J. Bronskill;Daniela Massiceti;Massimiliano Patacchiola;Katja Hofmann;Sebastian Nowozin;Richard E. Turner

How Tight Can PAC-Bayes be in the Small Data Regime?

PAC-Bayes 在小数据制度中可以有多严格？

• 发表时间: 2021
• 期刊: Advances in Neural Information Processing Systems
• 作者: Foong A.Y.K.

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

• 发表时间: 2020-06
• 期刊: ArXiv
• 作者: Chao Ma-;Sebastian Tschiatschek;José Miguel Hernández-Lobato;Richard E. Turner;Cheng Zhang

ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

• DOI: 10.1109/iccv48922.2021.01064
• 发表时间: 2021-04
• 期刊: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Daniela Massiceti;L. Zintgraf;J. Bronskill;Lida Theodorou;Matthew Tobias Harris;Edward Cutrell;C. Morrison;Katja Hofmann;Simone Stumpf