What do Russian trolls, Facebook, and US elections have to do with machine learning? Recommendation engines are at the heart of the central feedback loop of social networks and the user-generated content (UGC) they create. Users join the network and are recommended users and content with which to engage. Recommendation engines can be gamed because they amplify the effects of thought bubbles. The 2016 US presidential election showed how important it is to understand how recommendation engines work and the limitations and strengths they offer.

Here's a great talk from Build 2019 about the importance of design in creating Voice and chat virtual assistants. Designing a natural language interface can be difficult, is the interface supposed to be able to interpret every single nuance of speech? Or should we aim more towards forced language and make our users learn how to interact with simple commands? All the big companies are making huge investments in AI personal assistants. Amazon has Alexa, Google has Google assistant, Apple has Siri and Microsoft has Cortana to name a few.

Imagine a human-like teacher with no human flaws. The best educators in the world sometimes suffer from innate human errors, taking different forms in every one of us. They will eventually grow tired and nervous. Not even the best of them can provide personal attention to a class of 30. Computers never sleep; the knowledge they impart is available 24/7 across continents, time zones, and devices.

Amazon's Alexa voice assistant faces a massive challenge: Operating not only as a multi-lingual product, but also ensuring that all regional variants of languages it supports are well understood by Alexa, too. To help accomplish that, Alexa has been retrained entirely for every variant needed -- a time and resource-heavy activity. But a new machine learning-based method for training speech recognition created by Alexa's AI team could mean a lot less rework in building out models for new variants of existing languages. In a paper presented to the North American Chapter of the Association for Computational Linguistics, Amazon Alexa AI Senior Applied Science Manager Young-Bum Kim and his colleagues laid out a new system that was able to demonstrate improvements in accuracy of 18%, 43%, 115% and 57%, respectively, on four variants of English (from the U.S., the U.K., India and Canada) used in the trial. The team managed this by implementing a means through which it can tweak its learning algorithm to focus its attention more heavily on just a locale-specific model when it knows in advance that answers to requests from users made in that domain are highly region-specific (i.e. when asking to find a good nearby restaurant) versus when the results are going to be relatively similar regardless of where the request is being made. Alexa's team then combined their locale-specific models into one and also added their location-independent model for the language, and found the improvements measured above.

The Apple Watch Series 4 is the best smartwatch you can buy. There's no single killer feature that makes the Apple Watch Series 4 (as tested: 40mm with GPS and GPS/LTE), our pick for best smartwatch. It's the fact that it does almost everything better than every other smartwatch we've come across. That it can be used as a minimalist device, for keeping abreast of your smartphone notifications, or as an all-in wearable that will let you take or make phone calls, send text messages, navigate through a crowded city and listen to music without bringing your cellphone with you (provided you spring for the GPS/LTE version) is the icing on the cake. Setting up the Apple Watch to work with your iPhone is almost effortless. Using this watch, with its responsive OLED touchscreen display and rotating Digital Crown (Apple's marketing mumbo jumbo for the knob on the side of the watch) is just as easy. You can use your finger to navigate apps and menus, scroll through text with the Digital Crown or ask Siri to do some hands-free heavy lifting for you.

Matrix completion aims to reconstruct a data matrix based on observations of a small number of its entries. Usually in matrix completion a single matrix is considered, which can be, for example, a rating matrix in recommendation system. However, in practical situations, data is often obtained from multiple sources which results in a collection of matrices rather than a single one. In this work, we consider the problem of collective matrix completion with multiple and heterogeneous matrices, which can be count, binary, continuous, etc. We first investigate the setting where, for each source, the matrix entries are sampled from an exponential family distribution. Then, we relax the assumption of exponential family distribution for the noise and we investigate the distribution-free case. In this setting, we do not assume any specific model for the observations. The estimation procedures are based on minimizing the sum of a goodness-of-fit term and the nuclear norm penalization of the whole collective matrix. We prove that the proposed estimators achieve fast rates of convergence under the two considered settings and we corroborate our results with numerical experiments.

Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to users. While most of the recent interest has focused on providing local explanations, there has been a much lower emphasis on studying the effects of model dynamics and its impact on explanation. In this paper, we perform a focused study on the impact of model interpretability in the context of calibration. Specifically, we address the challenges of both over-confident and under-confident predictions with interpretability using attention distribution. Our results indicate that the means of using attention distributions for interpretability are highly unstable for un-calibrated models. Our empirical analysis on the stability of attention distribution raises questions on the utility of attention for explainability.

EVA's intelligent A.I. algorithms will automatically highlight key moments in conversation like action items and next steps. EVA listens for keywords in speech, but also recognizes intent. You can use voice commands to activate EVA to take notes or silently press the highlight button to not interrupt the flow of conversation. Customize your keywords so EVA highlights specific moments for you and your team.

At Amazon's re:Mars conference last week, the company rolled out Alexa Conversations in preview. Conversations is a module within the Alexa Skills Kit that stitches together Alexa voice apps into experiences that help you accomplish complex tasks. Alexa Conversations may be Amazon's most intriguing and substantial pitch to voice developers in years. Conversations will make creating skills possible with fewer lines of code. It will also do away with the need to understand the many different ways a person can ask to complete an action, as a recurrent neural network will automatically generate dialogue flow.

Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during inference. For instance, in the context of social recommendations, our framework would allow one user to request that their recommendations are invariant to both their age and gender, while also allowing another user to request invariance to just their age. Experiments on standard knowledge graph and recommender system benchmarks highlight the utility of our proposed framework.