Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.

1
25
下載
關閉預覽

相關內容

迄今為止,產品設計師最友好的交互動畫軟件。

What is Linux Linux file system Basic commands File permissions Variables Use HPC clusters Processes and jobs File editing

成為VIP會員查看完整內容
3
45
0

近年來,序列推薦係統這一新興的研究課題越來越受到人們的關注。與傳統的推薦係統(包括協同過濾和基於內容的過濾)不同,SRSs試圖理解和建模連續的用戶行為、用戶和條目之間的交互、以及用戶偏好和條目受歡迎程度隨時間的變化。SRSs涉及到以上幾個方麵,可以更準確地描述用戶上下文、意圖和目標,以及物品的消費趨勢。我們首先介紹了SRSs的特點,然後對該研究領域的關鍵挑戰進行了總結和分類,接著是相應的研究進展,包括該課題最新的和有代表性的進展。最後,討論了該領域的重要研究方向。

成為VIP會員查看完整內容
2
65
0

The tutorial is written for those who would like an introduction to reinforcement learning (RL). The aim is to provide an intuitive presentation of the ideas rather than concentrate on the deeper mathematics underlying the topic. RL is generally used to solve the so-called Markov decision problem (MDP). In other words, the problem that you are attempting to solve with RL should be an MDP or its variant. The theory of RL relies on dynamic programming (DP) and artificial intelligence (AI). We will begin with a quick description of MDPs. We will discuss what we mean by “complex” and “large-scale” MDPs. Then we will explain why RL is needed to solve complex and large-scale MDPs. The semi-Markov decision problem (SMDP) will also be covered.

The tutorial is meant to serve as an introduction to these topics and is based mostly on the book: “Simulation-based optimization: Parametric Optimization techniques and reinforcement learning” [4]. The book discusses this topic in greater detail in the context of simulators. There are at least two other textbooks that I would recommend you to read: (i) Neuro-dynamic programming [2] (lots of details on convergence analysis) and (ii) Reinforcement Learning: An Introduction [11] (lots of details on underlying AI concepts). A more recent tutorial on this topic is [8]. This tutorial has 2 sections: • Section 2 discusses MDPs and SMDPs. • Section 3 discusses RL. By the end of this tutorial, you should be able to • Identify problem structures that can be set up as MDPs / SMDPs. • Use some RL algorithms.

成為VIP會員查看完整內容
3
79
0

The State of Machine Learning Frameworks in 2019

In 2019, the war for ML frameworks has two remaining main contenders: PyTorch and TensorFlow. My analysis suggests that researchers are abandoning TensorFlow and flocking to PyTorch in droves. Meanwhile in industry, Tensorflow is currently the platform of choice, but that may not be true for long.

成為VIP會員查看完整內容
1
28
0

When I started out, I had a strong quantitative background (chemical engineering undergrad, was taking PhD courses in chemical engineering) and some functional skills in programming. From there, I first dove deep into one type of machine learning (Gaussian processes) along with general ML practice (how to set up ML experiments in order to evaluate your models) because that was what I needed for my project. I learned mostly online and by reading papers, but I also took one class on data analysis for biologists that wasn’t ML-focused but did cover programming and statistical thinking. Later, I took a linear algebra class, an ML survey class, and an advanced topics class on structured learning at Caltech. Those helped me obtain a broad knowledge of ML, and then I’ve gained deeper understandings of some subfields that interest me or are especially relevant by reading papers closely (chasing down references and anything I don’t understand and/or implementing the core algorithms myself).

成為VIP會員查看完整內容
2
50
0

The Growing Pushback Against Harmful AI,AI Now co-founders Kate Crawford and Meredith Whittaker opened the Symposium with a short talk summarizing some key moments of opposition over the year, focusing on five themes: (1) facial and affect recognition; (2) the movement from “AI bias” to justice; (3) cities, surveillance, borders; (4) labor, worker organizing, and AI, and; (5) AI’s climate impact. Below is an excerpt from their talk.

成為VIP會員查看完整內容
1
32
0

機器學習可解釋性,Interpretability and Explainability in Machine Learning

  • Overview As machine learning models are increasingly being employed to aid decision makers in high-stakes settings such as healthcare and criminal justice, it is important to ensure that the decision makers (end users) correctly understand and consequently trust the functionality of these models. This graduate level course aims to familiarize students with the recent advances in the emerging field of interpretable and explainable ML. In this course, we will review seminal position papers of the field, understand the notion of model interpretability and explainability, discuss in detail different classes of interpretable models (e.g., prototype based approaches, sparse linear models, rule based techniques, generalized additive models), post-hoc explanations (black-box explanations including counterfactual explanations and saliency maps), and explore the connections between interpretability and causality, debugging, and fairness. The course will also emphasize on various applications which can immensely benefit from model interpretability including criminal justice and healthcare.
成為VIP會員查看完整內容
2
58
0

Differentiable Graphics with TensorFlow 2.0

Deep learning has introduced a profound paradigm change in the recent years, allowing to solve significantly more complex perception problems than previously possible. This paradigm shift has positively impacted a tremendous number of fields with a giant leap forward in computer vision and computer graphics algorithms. The development of public libraries such as Tensorflow are in a large part responsible for the massive growth of AI. These libraries made deep learning easily accessible to every researchers and engineers allowing fast advances in developing deep learning techniques in the industry and academia. We will start this course with an introduction to deep learning and present the newly released TensorFlow 2.0 with a focus on best practices and new exciting functionalities. We will then show different tips, tools, and algorithms to visualize and interpret complex neural networks by using TensorFlow. Finally, we will introduce a novel TensorFlow library containing a set of graphics inspired differentiable layers allowing to build structured neural networks to solve various two and three dimensional perception tasks. To make the course interactive we will punctuate the presentations with real time demos in the form of Colab notebooks. Basic prior familiarity with deep learning will be assumed.** Deep learning has introduced a profound paradigm change in the recent years, allowing to solve significantly more complex perception problems than previously possible. This paradigm shift has positively impacted a tremendous number of fields with a giant leap forward in computer vision and computer graphics algorithms. The development of public libraries such as Tensorflow are in a large part responsible for the massive growth of AI. These libraries made deep learning easily accessible to every researchers and engineers allowing fast advances in developing deep learning techniques in the industry and academia. We will start this course with an introduction to deep learning and present the newly released TensorFlow 2.0 with a focus on best practices and new exciting functionalities. We will then show different tips, tools, and algorithms to visualize and interpret complex neural networks by using TensorFlow. Finally, we will introduce a novel TensorFlow library containing a set of graphics inspired differentiable layers allowing to build structured neural networks to solve various two and three dimensional perception tasks. To make the course interactive we will punctuate the presentations with real time demos in the form of Colab notebooks. Basic prior familiarity with deep learning will be assumed.

成為VIP會員查看完整內容
3
22
0

人工智能乳房x線照相術和數字化乳房人工合成:當前的概念和未來的展望綜述論文】Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives

成為VIP會員查看完整內容
0
3
0

主題:Neural Approaches to Conversational AI

摘要:開發一個智能對話係統,不僅可以模擬人類對話,還可以回答從電影明星的最新消息到愛因斯坦的相對論等各種主題的問題,並完成旅行計劃等複雜任務,一直是人工智能最長的目標之一。這一目標直到最近才實現。隨著大量的會話數據可用於訓練,深度學習(DL)和強化學習(RL)的突破被應用到會話人工智能中,我們在學術界和工業界都看到了有希望的結果。在本教程中,我們首先簡要介紹與對話人工智能相關的DL和RL的最新進展。然後,我們詳細描述了為三種對話係統或機器人開發的最先進的神經方法。第一個是問答機器人。QA bot具有從各種數據源(包括Web文檔和預編譯的知識圖)中提取的豐富知識,可以為用戶查詢提供簡潔直接的答案。第二個是麵向任務的對話係統,它可以幫助用戶完成從會議安排到假期計劃等任務。第三種是社交聊天聊天機器人,它能與人進行無縫、恰當的對話,經常扮演聊天夥伴和推薦者的角色。

邀請嘉賓:Michel Galley是微軟研究人工智能的高級研究員。他的研究興趣在自然語言處理和機器學習領域,特別關注會話人工智能、神經生成、統計機器翻譯和總結。他獲得了哥倫比亞大學的碩士和博士學位,並獲得了電子計算機科學學士學位。在加入微軟研究之前,他是斯坦福大學計算機係的研究助理。他還是南加州大學/國際科學院NLP小組和貝爾實驗室口語對話係統小組的定期訪問研究員。他與人合著了50多篇科學論文,其中許多出現在頂級的NLP、AI和ML會議上。其中兩份出版物是最佳論文決賽(NAACL 2010,EMNLP 2013)。他還擔任全國人民解放大會(ACL、NAACL、EMNLP)的地區主席,並在SIGIR和IJCAI擔任高級PC成員。

高劍鋒是微軟人工智能研究院的合作夥伴研究經理。他領導了人工智能係統的開發,用於機器閱讀理解(MRC)、問答(QA)、社交機器人、目標導向對話和商業應用。2014年至2017年,他擔任微軟研究院(Microsoft Research)深度學習技術中心(Deep Learning Technology Center)的合作研究經理,領導文本和圖像處理深度學習研究。從2006年到2014年,他是微軟研究中心(Microsoft Research)自然語言處理組的首席研究員,主要從事網絡搜索、查詢理解和重組、廣告預測和統計機器翻譯。從2005年到2006年,他是微軟自然交互服務部門的一名研究負責人,在那裏他參與了ProjectX,這是一項為Windows開發自然用戶界麵的工作。2000年至2005年,他在微軟亞洲研究院自然語言計算組擔任研究負責人,與同事們共同開發了微軟Office發布的首個中文語音識別係統,即市場上領先的中文/日文輸入法編輯器(IME),以及微軟Windows的自然語言平台。

成為VIP會員查看完整內容
1
13
0
小貼士
相關VIP內容
專知會員服務
45+閱讀 · 2020年7月26日
強化學習最新教程,17頁pdf
專知會員服務
79+閱讀 · 2019年10月11日
2019年機器學習框架回顧
專知會員服務
28+閱讀 · 2019年10月11日
機器學習入門的經驗與建議
專知會員服務
50+閱讀 · 2019年10月10日
【哈佛大學商學院課程Fall 2019】機器學習可解釋性
專知會員服務
58+閱讀 · 2019年10月9日
【SIGGRAPH2019】TensorFlow 2.0深度學習計算機圖形學應用
專知會員服務
22+閱讀 · 2019年10月9日
相關資訊
計算機 | ICDE 2020等國際會議信息8條
Call4Papers
3+閱讀 · 2019年5月24日
Transferring Knowledge across Learning Processes
CreateAMind
8+閱讀 · 2019年5月18日
CCF C類 | DSAA 2019 誠邀稿件
Call4Papers
3+閱讀 · 2019年5月13日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字閨中
10+閱讀 · 2018年12月24日
人工智能 | 國際會議信息10條
Call4Papers
5+閱讀 · 2018年12月18日
人工智能 | PRICAI 2019等國際會議信息9條
Call4Papers
4+閱讀 · 2018年12月13日
Disentangled的假設的探討
CreateAMind
8+閱讀 · 2018年12月10日
計算機 | CCF推薦會議信息10條
Call4Papers
3+閱讀 · 2018年10月18日
人工智能 | COLT 2019等國際會議信息9條
Call4Papers
6+閱讀 · 2018年9月21日
已刪除
將門創投
5+閱讀 · 2018年3月21日
Top
微信掃碼谘詢專知VIP會員
Top