We present and study models of adversarial online learning where the feedback observed by the learner is noisy, and the feedback is either full information feedback or bandit feedback. Specifically, we consider binary losses xored with the noise, which is a Bernoulli random variable. We consider both a constant noise rate and a variable noise rate. Our main results are tight regret bounds for learning with noise in the adversarial online learning model.

Robin E. was folding laundry when she heard her son talking to Alexa downstairs in a soft, hopeful voice. The 5-year-old was asking, "Alexa, will you be my friend?" Robin held her breath, waiting tensely for Alexa's response. Finally, she heard the assistant say, brightly, "I'm happy to be your friend." Robin and her husband have an Echo Spot in their bedroom and an Echo Show on their kitchen counter.

This beginner-friendly Python course will take you from zero to programming in Python in a matter of hours.

We introduce SimplerVoice: a key message and visual description generator system to help low-literate adults navigate the information-dense world with confidence, on their own. SimplerVoice can automatically generate sensible sentences describing an unknown object, extract semantic meanings of the object usage in the form of a query string, then, represent the string as multiple types of visual guidance (pictures, pictographs, etc.). We demonstrate SimplerVoice system in a case study of generating grocery products' manuals through a mobile application. To evaluate, we conducted a user study on SimplerVoice's generated description in comparison to the information interpreted by users from other methods: the original product package and search engines' top result, in which SimplerVoice achieved the highest performance score: 4.82 on 5-point mean opinion score scale. Our result shows that SimplerVoice is able to provide low-literate end-users with simple yet informative components to help them understand how to use the grocery products, and that the system may potentially provide benefits in other real-world use cases.

Pascal Weinberger in conversation with his team at Telefonica's "moonshots" division Alpha, where he heads AI research and development. Flying cars, augmented reality glasses and contact lenses that can detect diabetes: They're all innovations born out of Google X, the skunkworks division of Alphabet. Three years ago Spanish telco giant Telefónica established Alpha, a lab in Barcelona staffed by around 100 people, working in stealth on innovative technology that holds the promise of a potential new revenue streams. The person running all things AI at the lab is Pascal Weinberger, 21. Weinberger is originally from Germany and like many other computer programmers is self-taught.

DALLAS--(BUSINESS WIRE)--To solve humanity's most complex and demanding problems ranging from creating sustainable global food production and preventing infectious disease epidemics to ensuring the safety of our planet and natural resources is the HPC community's next grand challenge. HPC and AI are revolutionizing how we untangle and solve global threats and humanitarian crises. The SC18 plenary session will examine the potential for advanced computing to help mitigate human suffering and elevate our capacity to protect the most vulnerable. This plenary session will hear from innovators who are redefining how we predict and prevent humanitarian crises by leveraging advanced computing. The session is the kick-off event, which immediately precedes the Exhibitor Opening Gala.

Facebook is making some of the artificial intelligence it uses to prod people to chat and post more available for free. People can now use the social networking giant's Horizon coding tools to create their own software that can learn to do tasks in the most efficient way possible by trial-and-error. An outside developer working in her garage, for example, could use the sophisticated technology to build the next addictive app. "A hobbyist or high school student can run it on their laptop or you can run it on thousands of machines in the cloud," said Jason Gauci, Facebook's lead engineer for Horizon. Facebook, which announced the availability of the tool on Thursday, has used the technology to teach its computers to figure out which notifications users are most likely to respond to.

Personal electronic devices such as smartphones give access to a broad range of behavioral signals that can be used to learn about the characteristics and preferences of individuals. In this study we explore the connection between demographic and psychological attributes and digital records for a cohort of 7,633 people, closely representative of the US population with respect to gender, age, geographical distribution, education, and income. We collected self-reported assessments on validated psychometric questionnaires based on both the Moral Foundations and Basic Human Values theories, and combined this information with passively-collected multi-modal digital data from web browsing behavior, smartphone usage and demographic data. Then, we designed a machine learning framework to infer both the demographic and psychological attributes from the behavioral data. In a cross-validated setting, our model is found to predict demographic attributes with good accuracy (weighted AUC scores of 0.90 for gender, 0.71 for age, 0.74 for ethnicity). Our weighted AUC scores for Moral Foundation attributes (0.66) and Human Values attributes (0.60) suggest that accurate prediction of complex psychometric attributes is more challenging but feasible. This connection might prove useful for designing personalized services, communication strategies, and interventions, and can be used to sketch a portrait of people with similar worldviews.

Inverse optimization is a powerful paradigm for learning preferences and restrictions that explain the behavior of a decision maker, based on a set of external signal and the corresponding decision pairs. However, most inverse optimization algorithms are designed specifically in batch setting, where all the data is available in advance. As a consequence, there has been rare use of these methods in an online setting suitable for real-time applications. In this paper, we propose a general framework for inverse optimization through online learning. Specifically, we develop an online learning algorithm that uses an implicit update rule which can handle noisy data. Moreover, under additional regularity assumptions in terms of the data and the model, we prove that our algorithm converges at a rate of $\mathcal{O}(1/\sqrt{T})$ and is statistically consistent. In our experiments, we show the online learning approach can learn the parameters with great accuracy and is very robust to noises, and achieves a dramatic improvement in computational efficacy over the batch learning approach.

We focus on the task of multi-hop reading comprehension where a system is required to reason over a chain of multiple facts, distributed across multiple passages, to answer a question. Inspired by graph-based reasoning, we present a path-based reasoning approach for textual reading comprehension. It operates by generating potential paths across multiple passages, extracting implicit relations along this path, and composing them to encode each path. The proposed model achieves a 2.3% gain on the WikiHop Dev set as compared to previous state-of-the-art and, as a side-effect, is also able to explain its reasoning through explicit paths of sentences.