Efficient and Robust Machine Learning for Real-World Systems
Graz University of Technology(格拉茨工业大学);Ruperts Karls University(鲁珀特卡尔斯大学);Microsoft Research(微软研究院);University of Cambridge(剑桥大学);Uber AI Labs(优步人工智能实验室);Arm Research(Arm研究院);Arm Ltd.(Arm有限公司)
Franz Pernkopf, Wolfgang Roth, Matthias Zoehrer, Lukas Pfeifenberger, Guenther Schindler, Holger Froening, Sebastian Tschiatschek, Robert Peharz, Matthew Mattina, Zoubin Ghahramani
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. On top of this, it is crucial to treat uncertainty in a consistent manner in all but the simplest applications of machine learning systems. In particular, a desideratum for any real-world system is to be robust in the presence of outliers and corrupted data, as well as being `aware' of its limits, i.e.\ the system should maintain and provide an uncertainty estimate over its own predictions. These complex demands are among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology into every day's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. First we provide a comprehensive review of resource-efficiency in deep neural networks with focus on techniques for model size reduction, compression and reduced precision. These techniques can be applied during training or as post-processing and are widely used to reduce both computational complexity and memory footprint. As most (practical) neural networks are limited in their ways to treat uncertainty, we contrast them with probabilistic graphical models, which readily serve these desiderata by means of probabilistic inference. In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems.
Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction
Shenzhen Key Laboratory of Neuropsychiatric Modulation(深圳心理行为调控重点实验室);Shenzhen-Hong Kong Institute of Brain Science(深圳-香港脑科学研究院);Shenzhen Institutes of Advanced Technology(深圳先进技术研究院);Chinese Academy of Sciences(中国科学院)
Robust Machine Learning via Privacy/Rate-Distortion Theory
Mitsubishi Electric Research Laboratories(三菱电机研究实验室);Tufts University(塔夫茨大学);Arizona State University(亚利桑那州立大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Open-world machine learning: A review and new outlooks
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences(人工智能与机器人中心,香港科学与创新研究院,中国科学院);State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation of Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,中国科学院自动化研究所);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
A Robust Twin Parametric Margin Support Vector Machine for Multiclass Classification
School of Science and Technology, University of Camerino(科学与技术学院,坎皮诺大学);Department of Management, Information and Production Engineering, University of Bergamo(管理、信息与生产工程系,贝拉姆多大学)
Robust-MBDL: A Robust Multi-branch Deep Learning Based Model for Remaining Useful Life Prediction and Operational Condition Identification of Rotating Machines
University of Science and Technology - The University of Danang(岘港大学科技大学);Institute for Computational Science and Artificial Intelligence, Van Lang University(文郎大学计算科学与人工智能研究院);Van Lang University(文郎大学);AIT Austrian Institute of Technology GmbH(奥地利AIT技术研究院有限公司);University of Technology of Compiègne(贡比涅技术大学)
Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition
Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems(清华-香港中文大学媒体科学、技术与系统联合研究中心);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学)
A design of human-like robust AI machines in object identification
Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
本文是从图灵(A. M. Turing,1912年6月23日-1954年6月7日)在1950年提出的图灵测试研究中得到的启发而撰写的。根据图灵测试的一个重要含义,使机器具有类似人类的行为或性能,我们为AI机器定义了类似人类的鲁棒性(robustness,简称robustness)。新定义的目标是强制AI机器执行可扩展性,包括根据可扩展性来评估它们。一个特定的任务只讨论对象识别,因为它是每个人在日常生活中最常见的任务。与图灵的观点或设计立场类似,我们提供了一个解决方案,即如何在不构建机器和进行真实实验的情况下实现人工智能机器。解决方案应包括机器的三个重要特征。推理机的第一个特点是利用人类的常识来实现因果推理。第二个特征是从语义空间做出决策,以便对决策进行解释。第三个特点是包括一个“人在回路”的设置,以推进机器人。我们展示了一个“识别游戏”,使用建议的设计的机器。本文试图从图灵测试中学习和进一步探索类人AI机器的设计。
University of Trento(特伦托大学);University of Bergamo(贝加莫大学);Inria Grenoble(格勒诺布尔研究所);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)