Samsung's Q90R was arguably the best 4K UHD LED-backlit LCD TV of 2019. This year's Q90T is in line for equal status, with picture tweaks that eliminate--or ameliorate--some of my complaints from last year. My gripes about the Q90R were few and far between, so consider the Q90T the best getting better. There is, however, one major change: this will please some and disappoint others, but the One Connect breakout box is now history--all the Q90T's ports reside on the TV itself. If you want One Connect, your only option is the reportedly wonderful, but expensive ($13,000) 8K UHD Q950TS.

SmartRent, which provides smart home automation for property owners, managers, developers, and residents, today announced that it has raised $60 million. CEO Lucas Haldeman said the funding will enable the company's next phase of growth as it expands its portfolio of offerings. According to Statista, revenue from the smart home market is anticipated to climb 18.3% from 2020 to 2023, resulting in market volume of $41 billion within the next three years. But appliances, lighting fixtures, and security cameras are often not user-friendly, which has threatened to impede adoption. A survey conducted by TechSee found that nearly 74% of respondents were "certain" or "very likely" to return a new smart home purchase if they found it difficult to install.

Apple's Siri is supporting the Black Lives Matter movement by providing users who say'All Lives Matter' with a link to learn more about human rights initiative. When speaking the phrase to Siri, it will respond, 'All Lives Matter' is often used in response to phrase'Black Lives Matter,' but it does not represent the same concerns,' and then the technology prompts users to visit BlackLivesMatter.com. The update is to align with other businesses and organizations that are showing solidarity for the movement with worldwide protests following the death of George Floyd who was killed while in police custody last month. Apple also joins Amazon and Google, which have also updated their smart voice assistance to explain the Black Lives Matter movement to users. Apple's Siri is supporting the Black Lives Matter movement by providing users who say'All Lives Matter' with a link to learn more about human rights initiative Floyd was killed on May 25 in Minneapolis, Minnesota when Officer Derek Chauvin knelt on his neck until he lost consciousness – autopsies have since deemed the death a homicide.

The Android 11 beta is now available on all Pixel phones, bringing with it tweaks to how it handles notifications, media controls, payment interface, and many more smaller changes. The beta allows users to access pre-release features on Google's operating system, at the risk of some software bugs. One of the most important ways that Android has been updated is its notification menu, in an attempt to keep vital conversations separate from the barrage of other pop-ups users receive from every app. This is done by binning notifications into sections. The first is "Conversations", which is for messaging apps like Facebook Messenger, WhatsApp, and so on.

Machine learning has moved from the stuff of science fiction to a staple of modern business, as organizations across nearly every industry vertical implement ML technologies. Doctors are using machine learning to more accurately diagnosis and treat their patients, retailers are using ML to get the right merchandise to the right stores at the right time, and researchers are utilizing the technology to develop effective new medicines. That is just a sliver of the use cases emerging, as all sectors -- from energy and utilities, to travel and hospitality, to manufacturing to logistics -- and the various functions within any given organization increasingly put machine learning to work. Machine learning is a subset of artificial intelligence, where computers use algorithms to learn from data, allowing the machines to identify patterns -- a capability that organizations can put to use in multiple ways. Experts said machine learning enables organizations to perform tasks on a scale and scope previously impossible to achieve.

Collaborative Filtering (CF) has been an important approach to recommender systems. However, existing CF methods are mostly designed based on the idea of matching, i.e., by learning user and item embeddings from data using shallow or deep models, they try to capture the relevance patterns in data, so that a user embedding can be matched with appropriate item embeddings using designed or learned similarity functions. We argue that as a cognition rather than a perception intelligent task, recommendation requires not only the ability of pattern recognition and matching from data, but also the ability of logical reasoning in the data. Inspired by recent progress on neural-symbolic machine learning, we propose a neural collaborative reasoning framework to integrate the power of embedding learning and logical reasoning, where the embeddings capture similarity patterns in data from perceptual perspectives, and the logic facilitates cognitive reasoning for informed decision making. An important challenge, however, is to bridge differentiable neural networks and symbolic reasoning in a shared architecture for optimization and inference. To solve the problem, we propose a Modularized Logical Neural Network architecture, which learns basic logical operations such as AND, OR, and NOT as neural modules based on logical regularizer, and learns logic variables as vector embeddings. In this way, each logic expression can be equivalently organized as a neural network, so that logical reasoning and prediction can be conducted in a continuous space. Experiments on several real-world datasets verified the advantages of our framework compared with both traditional shallow and deep models.

Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning is essential to large-scale recommender systems. Standard approaches approximate maximum likelihood estimation (MLE) through sampling for better scalability and address the problem of DCG in a way similar to language modeling. However, live recommender systems face severe unfairness of exposure with a vocabulary several orders of magnitude larger than that of natural language, implying that (1) MLE will preserve and even exacerbate the exposure bias in the long run in order to faithfully fit the observed samples, and (2) suboptimal sampling and inadequate use of item features can lead to inferior representations for the unfairly ignored items. In this paper, we introduce CLRec, a Contrastive Learning paradigm that has been successfully deployed in a real-world massive recommender system, to alleviate exposure bias in DCG. We theoretically prove that a popular choice of contrastive loss is equivalently reducing the exposure bias via inverse propensity scoring, which provides a new perspective on the effectiveness of contrastive learning. We further employ a fixed-size queue to store the items' representations computed in previously processed batches, and use the queue to serve as an effective sampler of negative examples. This queue-based design provides great efficiency in incorporating rich features of the thousand negative items per batch thanks to computation reuse. Extensive offline analyses and four-month online A/B tests in Mobile Taobao demonstrate substantial improvement, including a dramatic reduction in the Matthew effect.

In session-based or sequential recommendation, it is important to consider a number of factors like long-term user engagement, multiple types of user-item interactions such as clicks, purchases etc. The current state-of-the-art supervised approaches fail to model them appropriately. Casting sequential recommendation task as a reinforcement learning (RL) problem is a promising direction. A major component of RL approaches is to train the agent through interactions with the environment. However, it is often problematic to train a recommender in an on-line fashion due to the requirement to expose users to irrelevant recommendations. As a result, learning the policy from logged implicit feedback is of vital importance, which is challenging due to the pure off-policy setting and lack of negative rewards (feedback). In this paper, we propose self-supervised reinforcement learning for sequential recommendation tasks. Our approach augments standard recommendation models with two output layers: one for self-supervised learning and the other for RL. The RL part acts as a regularizer to drive the supervised layer focusing on specific rewards(e.g., recommending items which may lead to purchases rather than clicks) while the self-supervised layer with cross-entropy loss provides strong gradient signals for parameter updates. Based on such an approach, we propose two frameworks namely Self-Supervised Q-learning(SQN) and Self-Supervised Actor-Critic(SAC). We integrate the proposed frameworks with four state-of-the-art recommendation models. Experimental results on two real-world datasets demonstrate the effectiveness of our approach.

Dozens of Tinder users were banned from the online dating app after mentioning Black Lives Matter in their profiles, according to Buzzfeed News. Some had added Black Lives Matter hashtags to their profiles, while others encouraged matches to sign petitions or donate to causes. According to BBC, Tinder's guidelines state that accounts can't be used for "promotional purposes," so the company may have been enforcing this rule when banning the accounts. However, it has reversed course, telling Buzzfeed News that it will act upon those terms "in line with our values." A spokesperson said that Tinder has "voiced our support for the Black Lives Matter movement and want our platform to be a place where our members can do the same."

Variational auto-encoder (VAE) is an efficient non-linear latent factor model that has been widely applied in recommender systems (RS). However, a drawback of VAE for RS is their inability of exploration. A good RS is expected to recommend items that are known to enjoy and items that are novel to try. In this work, we introduce an exploitation-exploration motivated VAE (XploVAE) to collaborative filtering. To facilitate personalized recommendations, we construct user-specific subgraphs, which contain the first-order proximity capturing observed user-item interactions for exploitation and the higher-order proximity for exploration. We further develop a hierarchical latent space model to learn the population distribution of the user subgraphs, and learn the personalized item embedding. Empirical experiments prove the effectiveness of our proposed method on various real-world data sets.