Artificial Intelligence (AI) is a computer or electronic device performing actions as if it were a human – it would apply some sort of intelligence factor or representation to accomplish the task. Some of these human services these electronic devices are performing include different planning methods and actions that include learning, problem solving, motion, thought manipulation, social response and intelligence, creativity, knowledge representation, and imitation. These electronic manipulations happening occur simultaneously with our daily lives, most of the time without us even realizing. Different examples of frequently used AI programming include virtual assistants (like Amazon's Alexa or Apple's Siri) photo recognition (like on social platforms and personal devices), and spam and credit card fraud testing; as well as more in-depth projects, like self-driving cars, check-out kiosks, and recommendation engines that frequent your past purchases to create their own ads. As consumers and participants in a fast-paced electronically changing world, we have not only let these AI infiltrations become a part of our daily lives, but we also have not educated ourselves on their pros and cons.

Facing a fridge full of ingredients but still don't know what to cook? Tired of following the same recipes and eager to try something new and creative? Thanks to AI technologies such as image recognition and machine learning, people can now save time, food and money in the kitchen while discovering creative and tasty recipes and even generating their own new and personalized flavours. Facebook has developed an image-to-recipe generation system which enables users to reverse engineer a recipe by simply inputting an image of the dish they want to prepare. First, ingredients and ingredient co-occurrence are generated by exploiting visual features extracted from the food image.

The recent development of online recommender systems has a focus on collaborative ranking from implicit feedback, such as user clicks and purchases. Different from explicit ratings, which reflect graded user preferences, the implicit feedback only generates positive and unobserved labels. While considerable efforts have been made in this direction, the well-known pairwise and listwise approaches have still been limited by various challenges. Specifically, for the pairwise approaches, the assumption of independent pairwise preference is not always held in practice. Also, the listwise approaches cannot efficiently accommodate "ties" due to the precondition of the entire list permutation. To this end, in this paper, we propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to inherently accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons and can be implemented with matrix factorization and neural networks. Meanwhile, we also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to $\sqrt{M/N}$, where $M$ and $N$ are the numbers of items and users, respectively. Finally, extensive experiments on four real-world datasets clearly validate the superiority of SetRank compared with various state-of-the-art baselines.

Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant. This makes it harder for the system to accurately detect intents, extract entities relevant to those intents and thereby perform the desired action. We present a neural model for scoping relevant information for the agent from a large query. We show that when used as a preprocessing step, the model improves performance of both intent detection and entity extraction tasks. We demonstrate the model's impact on Scheduler (Cortana is the persona of the agent, while Scheduler is the name of the service. We use them interchangeably in the context of this paper.) - a virtual conversational meeting scheduling assistant that interacts asynchronously with users through email. The model helps the entity extraction and intent detection tasks requisite by Scheduler achieve an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.

Matrix factorization (MF) has been widely applied to collaborative filtering in recommendation systems. Its Bayesian variants can derive posterior distributions of user and item embeddings, and are more robust to sparse ratings. However, the Bayesian methods are restricted by their update rules for the posterior parameters due to the conjugacy of the priors and the likelihood. Neural networks can potentially address this issue by capturing complex mappings between the posterior parameters and the data. In this paper, we propose a variational auto-encoder based Bayesian MF framework. It leverages not only the data but also the information from the embeddings to approximate their joint posterior distribution. The approximation is an iterative procedure with cross feedback of user and item embeddings to the others' encoders. More specifically, user embeddings sampled in the previous iteration, alongside their ratings, are fed back into the item-side encoders to compute the posterior parameters for the item embeddings in the current iteration, and vice versa. The decoder network then reconstructs the data using the MF with the currently re-sampled user and item embeddings. We show the effectiveness of our framework in terms of reconstruction errors across five real-world datasets. We also perform ablation studies to illustrate the importance of the cross feedback component of our framework in lowering the reconstruction errors and accelerating the convergence.

The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years. The necessity of encoding complex relational dependencies among the features and variables for competent predictions require the development of fair, yet expressive relational models. In this work, we introduce Fair-A3SL, a fairness-aware structure learning algorithm for learning relational structures, which incorporates fairness measures while learning relational graphical model structures. Our approach is versatile in being able to encode a wide range of fairness metrics such as statistical parity difference, overestimation, equalized odds, and equal opportunity, including recently proposed relational fairness measures. While existing approaches employ the fairness measures on pre-determined model structures post prediction, Fair-A3SL directly learns the structure while optimizing for the fairness measures and hence is able to remove any structural bias in the model. We demonstrate the effectiveness of our learned model structures when compared with the state-of-the-art fairness models quantitatively and qualitatively on datasets representing three different modeling scenarios: i) a relational dataset, ii) a recidivism prediction dataset widely used in studying discrimination, and iii) a recommender systems dataset. Our results show that Fair-A3SL can learn fair, yet interpretable and expressive structures capable of making accurate predictions.

Online dating going mainstream hasn't made the potential dangers of meeting up with an internet stranger any less alarming. That's why Match.com is rolling out a check-in feature that lets users shoot over their date details to trusted confidantes, including the name of the person they're meeting up with, the location of the date and the time. Once check-in is turned on, users will receive an automated text message during their date asking them if everything is going alright and if they'd like to notify their previously listed emergency contacts if it's not. Match.com is letting users notify emergency contacts if their date is showing any red flags. Check-in sends users a text that users can reply to and send trusted contacts their date's name, the location of the date and the time The user can then reply'yes' to the text message and all three contacts will be notified.

Smart speakers, such as Amazon Echo, have been adopted by millions of users. However, the privacy impacts of smart speakers have not been well examined. We investigate the privacy leakage of smart speakers under an encrypted traffic analysis attack, referred to as voice command fingerprinting. In this attack, an adversary eavesdrops encrypted voice traffic from and to a smart speaker and infers which voice command a user says without decrypting encrypted traffic. We design our attacks based on neural networks and collect two large-scale datasets on Amazon Echo and Google Home by using an automatic traffic crawler.

If you go down to the farm today, you'll likely find it packed with sensors, drones and remote management systems run by iPhones, iPads and other mobile devices. In fact, we're only one or two Siri Shortcuts away from voice-controlled farms equipped with remotely controlled irrigation, livestock and crop management solutions and blockchain-based crop lifecycle analysis tools. Most of this technology exists, but cost constrains deployment. Leading the digital transformation of agriculture are apps, such as: Agrellus, an online marketplace for agriculture, xarvio Scouting App for better crop management, FieldNET Mobile to control water pivots remotely, Yara ImageIT, which turns your iPhone into a crop nutrient testing system, AgSense, and GrainTruckPlus. There are many more apps for agriculture available at the App Store – including Tudder, the "Tinder for farm animals."

Point-of-Interest (POI) recommendation is one of the most important location-based services helping people discover interesting venues or services. However, the extreme user-POI matrix sparsity and the varying spatio-temporal context pose challenges for POI systems, which affects the quality of POI recommendations. To this end, we propose a translation-based relation embedding for POI recommendation. Our approach encodes the temporal and geographic information, as well as semantic contents effectively in a low-dimensional relation space by using Knowledge Graph Embedding techniques. To further alleviate the issue of user-POI matrix sparsity, a combined matrix factorization framework is built on a user-POI graph to enhance the inference of dynamic personal interests by exploiting the side-information. Experiments on two real-world datasets demonstrate the effectiveness of our proposed model.