Meta-learning extracts the common knowledge acquired from learning different tasks and uses it for unseen tasks. It demonstrates a clear advantage on tasks that have insufficient training data, e.g., few-shot learning. In most meta-learning methods, tasks are implicitly related via the shared model or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve the performance of few-shot learning. This type of graph is usually free or cheap to obtain but has rarely been explored in previous works. We study the prototype based few-shot classification, in which a prototype is generated for each class, such that the nearest neighbor search between the prototypes produces an accurate classification. We introduce "Gated Propagation Network (GPN)", which learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism is used for the aggregation of messages from neighboring classes, and a gate is deployed to choose between the aggregated messages and the message from the class itself. GPN is trained on a sequence of tasks from many-shot to few-shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, we change the training-test discrepancy and test task generation settings for thorough evaluations. GPN outperforms recent meta-learning methods on two benchmark datasets in all studied cases.

Multiple Instance learning (MIL) algorithms are tasked with learning how to associate sets of elements with specific set-level outputs. Towards this goal, the main challenge of MIL lies in modelling the underlying structure that characterizes sets of elements. Existing methods addressing MIL problems are usually tailored to address either: a specific underlying set structure; specific prediction tasks, e.g. classification, regression; or a combination of both. Here we present an approach where a set representation is learned, iteratively, by looking at the constituent elements of each set one at a time. The iterative analysis of set elements enables our approach with the capability to update the set representation so that it reflects whether relevant elements have been detected and whether the underlying structure has been matched. These features provide our method with some model explanation capabilities. Despite its simplicity, the proposed approach not only effectively models different types of underlying set structures, but it is also capable of handling both classification and regression tasks - all this while requiring minimal modifications. An extensive empirical evaluation shows that the proposed method is able to reach and surpass the state-of-the-art.

AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best AI system achieved merely 59.3% on an 8th Grade science exam challenge. This paper reports unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam's non-diagram, multiple choice (NDMC) questions. In addition, our Aristo system, building upon the success of recent language models, exceeded 83% on the corresponding Grade 12 Science Exam NDMC questions. The results, on unseen test questions, are robust across different test years and different variations of this kind of test. They demonstrate that modern NLP methods can result in mastery on this task. While not a full solution to general question-answering (the questions are multiple choice, and the domain is restricted to 8th Grade science), it represents a significant milestone for the field.

For most of the past sixty years, a rich critique of artificial intelligence was avidly pursued, mostly by insiders, people either practicing AI or interested onlookers who were in close proximity. Now the world finds itself in a strange state: Just as AI has gone mainstream, showing up everywhere from your Instagram feed to your smartphone voice assistant, many of those voices of criticism have been lost as a generation of thinkers passed away, people like MIT scientist Marvin Minsky and UC Berkeley professor of philosophy Herbert Dreyfus. But a small contingent of critics remains, and the world needs them to keep a balance in its view of AI as the use of AI becomes more entwined with everyday life. They include Judea Pearl, whose Book of Why reminds AI practitioners of the need for causal reasoning; and University of Toronto professor Hector Levesque, whose test for common sense, the Winograd Schema Challenge, sets a high bar for conventional AI. But none have been more prolific in the modern era in the critique of AI than NYU professor of psychology Gary Marcus. In five books and numerous articles in popular publications such as The New York Times and The New Yorker, Marcus has skewered the latest AI headlines, to remind people of the limits to present AI.

Artificial intelligence researchers have long dreamed of building a computer as knowledgeable and communicative as the one in Star Trek, which could interact with humans in natural (i.e., human) language. Last week, we seemed to boldly go toward that ideal. The New York Times reported that a team at the Allen Institute for Artificial Intelligence (AI2) had achieved "an artificial-intelligence milestone." AI2's program, Aristo, not only passed but also excelled on a standardized eighth-grade science test. The machine, the Times heralded, "is ready for high school science. Melanie Mitchell is professor of computer science at Portland State University and External Professor at the Santa Fe Institute. Her book Artificial Intelligence: A Guide for Thinking Humans will be published in October by Farrar, Straus, and Giroux. Aristo isn't the first AI system to shine on a test designed to gauge human knowledge and reasoning abilities. In 2015 one system matched a 4-year-old's performance on an ...

Artificial Intelligence today is where personal computers were back in the 90s: a new skill that everyone will have to become familiar with within the next few years. What if you could be as familiar with AI as you are with MS Office? Why this course: The problem at hand is that while there are not enough data scientists and engineers to create AI solutions, there are even fewer managers and leaders who know how to apply AI to business or organizational problems in the right manner, or have the time to learn it in detail. The good news, however, is that just like with computers, most of us do not need to learn how to code to understand and use AI well. This course will help you get a thorough understanding of AI techniques & how to use/manage them, to support your career as well as your organization's growth. It will also clear the confusion around what AI can or cannot do, and will allow you to spot strong or weak AI solutions - all in under 3 hours.

Save on the things that will make the school year easier. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. There are few things in life that get me excited in the middle of the workweek--and one of those things is a good deal. The kind of deal that's so good on a product you've been eyeing for a while that it makes you want to shout about it from the rooftop.

Rachelle Dene Poth is a foreign language and STEAM teacher at Riverview Junior/Senior High in Oakmont, Pennsylvania. Over the past year, I have focused on learning more about artificial intelligence. I thought I understood the meaning of AI. In early 2018, I noticed that AI was becoming an increasingly popular topic of discussion in the blogs that I was reading and in social media posts. When I first started thinking of AI, I had a flashback to the 2004 movie I, Robot, which starred Will Smith.

Wouldn't it be fabulous to know for sure that an article you read online is authentic and contains trusted sources? If everyone used AI to fact check, fake news and data could be eliminated permanently from online news sites. Menlo Park, CA-based AI startup, Diffbot has announced an official partnership with the European Journalism Centre to combat fake news. The company is the only other US company aside from Microsoft and Google to crawl and index the entire web to create its Knowledge Graph. Journalists can access the DKG through the Data Journalism platform created by the European Journalism Centre to provide resources, materials, online courses and community forums for data journalists all over the world.

Recent surveys, studies, forecasts and other quantitative assessments of the impact and progress of AI highlighted the need to retrain many workers, improving AI's score from F to A on 8th-grade science exam, and the $97.9 billion the AI market will reach in 2023. In the next three years, as many as 120 million workers in the world's 12 largest economies may need to be retrained or reskilled as a result of AI and intelligent automation; only 41% of CEOs surveyed say that they have the people, skills and resources required to execute their business strategies; the time it takes to close a skills gap through training has increased from 3 days on average in 2014 to 36 days in 2018 [IBM] Top drivers for investing in robotics and automation: Reduced cost (80%), improved quality (55%), increased productivity (54%), improved capabilities of robots (54%). "I was at MIT for another fifteen years after I graduated…twenty years after I went and asked to do my bachelor's thesis [with Victor Zue on speech recognition], Siri comes out… twenty years ago, we [wanted to] have a device where you can talk to it and it gives you answers and twenty years later there it was. So, that, for me, that was a cue that maybe it's time to go where the action is, which was in companies that were building these things. Once you have a large company like Microsoft or Google throwing their resources behind these hard problems, then you can't compete when you're in academia for that space. You know, you have to move on to something harder and more far out… So, I joined Microsoft to work on Cortana…"--T.J. Hazen The worldwide market for AI systems will reach $97.9 billion in 2023, up from $37.5 billion in 2019.