In general, recommendation can be viewed as a matching problem, i.e., match proper items for proper users. However, due to the huge semantic gap between users and items, it's almost impossible to directly match users and items in their initial representation spaces. To solve this problem, many methods have been studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods. Representation learning-based CF methods try to map users and items into a common representation space. In this case, the higher similarity between a user and an item in that space implies they match better. Matching function learning-based CF methods try to directly learn the complex matching function that maps user-item pairs to matching scores. Although both methods are well developed, they suffer from two fundamental flaws, i.e., the limited expressiveness of dot product and the weakness in capturing low-rank relations respectively. To this end, we propose a general framework named DeepCF, short for Deep Collaborative Filtering, to combine the strengths of the two types of methods and overcome such flaws. Extensive experiments on four publicly available datasets demonstrate the effectiveness of the proposed DeepCF framework.

ESPN is making some welcome (and arguably overdue) improvements to its ESPN service that could change how and where you watch. Its updated app now includes personalized recommendations for ESPN, starting with on-demand videos. You'll probably see more highlight clips from the latest NHL matches. Recommendations will "soon" spread to live and future events, so you might spot big matches you would otherwise miss. The company is also borrowing a page from Netflix and other services by introducing offline viewing.

From business innovations and media headlines to TV and movies, it seems that artificial intelligence (AI) is virtually everywhere. While still in its early stages across the financial services industry, AI adoption is expected to accelerate over the next few years. And it's expected to save companies big bucks. According to a recent study by Accenture, 77% of banks plan to use AI to automate tasks to a large extent in the next 3 three years. In addition, a recent study by Autonomous Next, indicates the potential cost savings of using AI could total $450 billion across the banking industry by 2030.

Google this week debuted a slew of new capabilities for its artificial intelligence software, Google Assistant, at CES in Las Vegas. One of the headliners was a preview of Google Assistant Connect. The new platform lets device manufacturers incorporate Google Assistant into their products easily and cost-effectively. Connect uses Google's existing smart home platform to expand to new device types, while making device setup and discovery easy for consumers. A manufacturer could create a continuous e-ink display projecting weather or calendar information, for example, while using Connect to drive content from a linked smart speaker.

Artificial Intelligence (AI) can and will underpin many of the upcoming changes affecting organizations as a whole, but especially IT departments. AI is being hailed as the cornerstone of the Fourth Industrial Revolution, with the potential to completely overhaul the way we live and work. Much of the focus around AI has been on the threat to jobs and displacing the need for humans; savvy organisations already realise that the real risk around this emerging technology is failure to embrace the productivity benefits on offer. IT departments not already involved in AI projects should move quickly to understand how the technology can improve their performance and that of the wider organization, as it will be down to them to embed AI across business applications and IT platforms. Thanks to recent advancements in machine learning, and the convergence of cloud compute power and big data, AI is finally making its way into the mainstream, with user-friendly systems available for organizations of all shapes and sizes.

Baby Shark,

Apple is finally launching HomePod in China, but the timing is tricky as the premium device will have to wrestle with local competitors and a slowing economy. The firm said over the weekend that its smart speaker will be available in Mainland China and Hong Kong starting January 18, adding to a list of countries where it has entered including US, UK, Australia, Canada, France, Germany, Mexico and Spain. The Amazon Echo competitor, which launched in mid-2017, is already available to Chinese buyers through third-party channels like "daigou", or shopping agents who bring overseas products into China. What separates the new model is that it supports Mandarin, the official language on Mainland China and Cantonese, which is spoken in Hong Kong and China's most populated province Guangdong. Previously, Chinese-speaking users had to converse with HomePod in English until a system update in December that added Siri support for the two Chinese dialects.

Will is a serial swiper, Alvin says he's addicted, and Meggy is about to give up. Dating apps are everywhere, but how do they affect our mental health?

Artificial intelligence (AI) has infiltrated numerous aspects of our lives in recent years, thanks to improvements in the field of machine learning, where computers ostensibly program themselves. This drive towards digital self-learning has led to major breakthroughs in our day-to-day interactions with machines, most notably the rise of digital home assistants such as Amazon Echo, and the recently launched Google Lens, which identifies objects based on visual cues from your phone's camera. One of the most widely-discussed advances has been the use of AI in translation. Not unlike the Babel Fish from The Hitchhiker's Guide to the Galaxy, with AI translation, "you can instantly understand anything said to you in any form of language." The technology works by recognizing words individually and then, as MIT Technology Review puts it, "takes advantage of the fact that relationships between certain words…are similar across languages" to create its translations. It has already found its way into a number of our most commonly used websites and platforms, with even grander plans in the pipeline – but just how reliable is the technology?

This paper presents a non-trivial reconstruction of a previous joint topic-sentiment-preference review model TSPRA with stick-breaking representation under the framework of variational inference (VI) and stochastic variational inference (SVI). TSPRA is a Gibbs Sampling based model that solves topics, word sentiments and user preferences altogether and has been shown to achieve good performance, but for large data set it can only learn from a relatively small sample. We develop the variational models vTSPRA and svTSPRA to improve the time use, and our new approach is capable of processing millions of reviews. We rebuild the generative process, improve the rating regression, solve and present the coordinate-ascent updates of variational parameters, and show the time complexity of each iteration is theoretically linear to the corpus size, and the experiments on Amazon data sets show it converges faster than TSPRA and attains better results given the same amount of time. In addition, we tune svTSPRA into an online algorithm ovTSPRA that can monitor oscillations of sentiment and preference overtime. Some interesting fluctuations are captured and possible explanations are provided. The results give strong visual evidence that user preference is better treated as an independent factor from sentiment.