AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding criteria, as there are additional constraints and/or priorities imposed by regulations, values, preferences, or ethical principles. We detail a novel online agent that learns a set of behavioral constraints by observation and uses these learned constraints as a guide when making decisions in an online setting while still being reactive to reward feedback. To define this agent, we propose to adopt a novel extension to the classical contextual multi-armed bandit setting and we provide a new algorithm called Behavior Constrained Thompson Sampling (BCTS) that allows for online learning while obeying exogenous constraints. Our agent learns a constrained policy that implements the observed behavioral constraints demonstrated by a teacher agent, and then uses this constrained policy to guide the reward-based online exploration and exploitation. We characterize the upper bound on the expected regret of the contextual bandit algorithm that underlies our agent and provide a case study with real world data in two application domains. Our experiments show that the designed agent is able to act within the set of behavior constraints without significantly degrading its overall reward performance.

Rank minimization (RM) is a wildly investigated task of finding solutions by exploiting low-rank structure of parameter matrices. Recently, solving RM problem by leveraging non-convex relaxations has received significant attention. It has been demonstrated by some theoretical and experimental work that non-convex relaxation, e.g. Truncated Nuclear Norm Regularization (TNNR) (Hu et al., 2013) and Reweighted Nuclear Norm Regularization (RNNR) (Zhong et al., 2015), can provide a better approximation of original problems than convex relaxations. However, designing an efficient algorithm with theoretical guarantee remains a challenging problem. In this paper, we propose a simple but efficient proximal-type method, namely Iterative Shrinkage-Thresholding Algorithm(ISTA), with concrete analysis to solve rank minimization problems with both non-convex weighted and reweighted nuclear norm as low-rank regularizers. Theoretically, the proposed method could converge to the critical point under very mild assumptions with the rate in the order of O(1/T). Moreover, the experimental results on both synthetic data and real world data sets show that proposed algorithm outperforms state-of-arts in both efficiency and accuracy.

In this paper, we demonstrate novel ways in which the synthesis of these data can illuminate the terrain of users' environment and support them in their decision making and wayfinding. A novel application of Recurrent Neural Networks and skip-gram models, approaches popularized by their application to modeling language, are brought to bear on student university enrollment sequences to create vector representations of courses and map out traversals across them. We present demonstrations of how scrutability from these neural networks can be gained and how the combination of these techniques can be seen as an evolution of content tagging and a means for a recommender to balance user preferences inferred from data with those explicitly specified. From validation of the models to the development of a UI, we discuss additional requisite functionality informed by the results of a field study leading to the ultimate deployment of the system at a university.

There is no shortage of debate when it comes to the use of artificial intelligence in the workplace. Some believe the technology will cost them their jobs, while others worry about security. A growing body of research, however, points to the narrative that intelligence will only diversify human thinking, not replace it. A recent study by Tata Communications, which was based on the inputs of 120 business leaders from across the world, says nine in 10 respondents agree that cognitive diversity is important for management and 93% believe AI will enhance decision making. What's more, three in four business leaders expect AI to produce new positions for their workers.

Recommender systems are used in variety of domains affecting people's lives. This has raised concerns about possible biases and discrimination that such systems might exacerbate. There are two primary kinds of biases inherent in recommender systems: observation bias and bias stemming from imbalanced data. Observation bias exists due to a feedback loop which causes the model to learn to only predict recommendations similar to previous ones. Imbalance in data occurs when systematic societal, historical, or other ambient bias is present in the data. In this paper, we address both biases by proposing a hybrid fairness-aware recommender system. Our model provides efficient and accurate recommendations by incorporating multiple user-user and item-item similarity measures, content, and demographic information, while addressing recommendation biases. We implement our model using a powerful and expressive probabilistic programming language called probabilistic soft logic. We experimentally evaluate our approach on a popular movie recommendation dataset, showing that our proposed model can provide more accurate and fairer recommendations, compared to a state-of-the art fair recommender system.

Current dialogue systems focus more on textual and speech context knowledge and are usually based on two speakers. Some recent work has investigated static image-based dialogue. However, several real-world human interactions also involve dynamic visual context (similar to videos) as well as dialogue exchanges among multiple speakers. To move closer towards such multimodal conversational skills and visually-situated applications, we introduce a new video-context, many-speaker dialogue dataset based on live-broadcast soccer game videos and chats from Twitch.tv. This challenging testbed allows us to develop visually-grounded dialogue models that should generate relevant temporal and spatial event language from the live video, while also being relevant to the chat history. For strong baselines, we also present several discriminative and generative models, e.g., based on tridirectional attention flow (TriDAF). We evaluate these models via retrieval ranking-recall, automatic phrase-matching metrics, as well as human evaluation studies. We also present dataset analyses, model ablations, and visualizations to understand the contribution of different modalities and model components.

Smart speakers are rapidly becoming a fixture in our households. That's according to Adobe, which found in a poll of US consumers that nearly half could own a smart speaker by the end of the year. In fact, smart speakers are already in roughly a third of US households, meaning we're not far off from hitting the 50 percent mark. Smart speakers are becoming a fixture in our households. That's according to Adobe, which found in a poll of US consumers that nearly half could own one by the end of the year Smart speaker use has already experienced a rapid increase in just the past few months, Adobe said.

Your Google Home may soon be able to help you fall asleep at night. The search giant is planning to introduce its suite of Digital Wellbeing features to Google Assistant and Home smart speakers, according to 9to5Google. Google unveiled the Digital Wellbeing tools at its annual I/O developers conference earlier this year as a way for users to cut down on smartphone use each day. Your Google Home may soon be able to help you fall asleep at night. Details in application package kit (APK) associated with the latest Google app for Android revealed that such features were coming to its voice-activated devices and as a skill for its digital assistant. There now includes a'Digital wellbeing' setting, as well as another setting called'Downtime,' 9to5Google noted.

Online dating service OkCupid now allows its non-binary and LGBT users to choose their pronoun. Once they've selected their gender(s) from their profile, they can either select from a trio of options (she/her, he/him and they/them) or type in their chosen pronoun. Once entered, it will show up in the'details' section alongside gender and sexual orientation for others to publicly see. This follows Grindr's move last November allowing folks pick their pronouns to better include the app's transgender users. OkCupid added pronouns to help LGBTQ daters, per the company's blog post, to affirm those who want to share it with potential partners.

Earlier this year, Tinder began testing out a feature that serves up a list of curated profiles for users who were willing to pay a few extra bucks each month. Now, the popular dating app has announced that the feature, called'Top Picks,' is now launching worldwide. However, it's only available for paying subscribers of Tinder Gold, which costs £7.49 Tinder announced that'Top Picks' is now available worldwide. Top Picks quietly launched in the US and UK last week, after it was tested in Germany, Brazil, France, Canada, Turkey, Mexico, Sweden, Russia and the Netherlands, according to TechCrunch.