Calibrated estimates of uncertainty are critical for many real-world computer vision applications of deep learning. While there are several widely-used uncertainty estimation methods, dropout inference stands out for its simplicity and efficacy. This technique, however, requires multiple forward passes through the network during inference and therefore can be too resource-intensive to be deployed in real-time applications. We propose a simple, easy-to-optimize distillation method for learning the conditional predictive distribution of a pre-trained dropout model for fast, sample-free uncertainty estimation in computer vision tasks. We empirically test the effectiveness of the proposed method on both semantic segmentation and depth estimation tasks and demonstrate our method can significantly reduce the inference time, enabling real-time uncertainty quantification, while achieving improved quality of both the uncertainty estimates and predictive performance over the regular dropout model.

We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification. It challenges models to extract facts from several Wikipedia articles that are relevant to a claim and classify whether the claim is Supported or Not-Supported by the facts. In HoVer, the claims require evidence to be extracted from as many as four English Wikipedia articles and embody reasoning graphs of diverse shapes. Moreover, most of the 3/4-hop claims are written in multiple sentences, which adds to the complexity of understanding long-range dependency relations such as coreference. We show that the performance of an existing state-of-the-art semantic-matching model degrades significantly on our dataset as the number of reasoning hops increases, hence demonstrating the necessity of many-hop reasoning to achieve strong results. We hope that the introduction of this challenging dataset and the accompanying evaluation task will encourage research in many-hop fact retrieval and information verification. We make the HoVer dataset publicly available at https://hover-nlp.github.io

We propose EXAMS -- a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. We collected more than 24,000 high-quality high school exam questions in 16 languages, covering 8 language families and 24 school subjects from Natural Sciences and Social Sciences, among others. EXAMS offers a fine-grained evaluation framework across multiple languages and subjects, which allows precise analysis and comparison of various models. We perform various experiments with existing top-performing multilingual pre-trained models and we show that EXAMS offers multiple challenges that require multilingual knowledge and reasoning in multiple domains. We hope that EXAMS will enable researchers to explore challenging reasoning and knowledge transfer methods and pre-trained models for school question answering in various languages which was not possible before. The data, code, pre-trained models, and evaluation are available at https://github.com/mhardalov/exams-qa.

The 2nd edition of the Montreal AI Ethics Institute's The State of AI Ethics captures the most relevant developments in the field of AI Ethics since July 2020. This report aims to help anyone, from machine learning experts to human rights activists and policymakers, quickly digest and understand the ever-changing developments in the field. Through research and article summaries, as well as expert commentary, this report distills the research and reporting surrounding various domains related to the ethics of AI, including: AI and society, bias and algorithmic justice, disinformation, humans and AI, labor impacts, privacy, risk, and future of AI ethics. In addition, The State of AI Ethics includes exclusive content written by world-class AI Ethics experts from universities, research institutes, consulting firms, and governments. These experts include: Danit Gal (Tech Advisor, United Nations), Amba Kak (Director of Global Policy and Programs, NYU's AI Now Institute), Rumman Chowdhury (Global Lead for Responsible AI, Accenture), Brent Barron (Director of Strategic Projects and Knowledge Management, CIFAR), Adam Murray (U.S. Diplomat working on tech policy, Chair of the OECD Network on AI), Thomas Kochan (Professor, MIT Sloan School of Management), and Katya Klinova (AI and Economy Program Lead, Partnership on AI). This report should be used not only as a point of reference and insight on the latest thinking in the field of AI Ethics, but should also be used as a tool for introspection as we aim to foster a more nuanced conversation regarding the impacts of AI on the world.

Today's highlighted deal comes via our Online Courses section of the Neowin Deals store, where you can save 97% off the Ultimate Python & Artificial Intelligence Certification Bundle. This Ultimate Python & Artificial Intelligence Certification Bundle normally costs* $1,791, but you can pick it up for just $39.99 for a limited time that's a saving of $1,751.01 Get this deal, or learn more about it here See all discounted Online Courses on offer. This is a time-limited deal. Get $1 credit for every $25 spent · Give $10, Get $10 · 10% off for first-time buyers.

It is certainly an understatement to say that Rashida Hodge is an inspiration. A tenacious, 18-year tech exec, Hodge has forged an impressive career centered on exploration, expanding representation, and philanthropy. In her current role at IBM, Hodge leads product integration of artificial intelligence and other emerging technologies for key IBM clients in North America. Hodge's story will certainly motivate anyone who has the pleasure of meeting her but may be especially useful to women and people of color looking to begin a career in STEM. After our powerful discussion, it became clear that the natural choice was to let Hodge's story be told in her own, kind and confident voice. We began our conversation by discussing Hodge's childhood and early career, during which she explained how family support propelled her towards a love for and career in engineering.

Artificial intelligence has been front and center in recent months. The global pandemic has pushed governments and private companies worldwide to propose AI solutions for everything from analyzing cough sounds to deploying disinfecting robots in hospitals. These efforts are part of a wider trend that has been picking up momentum: the deployment of projects by companies, governments, universities, and research institutes aiming to use AI for societal good. The goal of most of these programs is to deploy cutting-edge AI technologies to solve critical issues such as poverty, hunger, crime, and climate change, under the "AI for good" umbrella. But what makes an AI project good?

Ever since the dawn of the internet and computer processors people have been discussing to what extent artificial intelligence will begin to replace or supersede human modes of organisation and production. While many academic papers have been written and countless articles and books penned on the subject, there is one field which routinely acts as artificial intelligence's training ground. That field is of course online gaming. These days whether you are playing a battle royale game on a cloud platform or you are competing in an online chess competition, you can almost be certain that some element of AI technology will be either working for you or very much against you. In this article we look at the games that have been altered unimaginably by AI from what they used to be, as well as at how the technology could be used to greater effect in the near future.

In this section we will learn - What does Machine Learning mean. What are the meanings or different terms associated with machine learning? You will see some examples so that you understand what machine learning actually is. It also contains steps involved in building a machine learning model, not just linear models, any machine learning model.

Preview this course - GET COUPON CODE Convolutional neural networks with mathematical derivations and practical applications is the second course in my Neural Networks and deep learning series, after the first course in the series named "College-Level Neural Networks With Mathematical Derivations". As the title implies, This course is focused on Convolutional neural networks, a special kind of neural networks mainly used for visual recognition in images and videos, yet not limited to that. In this course, I mainly focus on concepts, intuitions, mathematical derivations, and practical applications. The course is mainly divided into 4 chapters: Chapter 1 focuses on the conceptual basics and intuitions of CNNs. Why are they suitable for visual recognition? Chapter 2 takes a step deeper into the CNN mathematical derivations.