Everything has its time, which is also true in the point-of-interest (POI) recommendation task. A truly intelligent recommender system, even if you don't visit any sites or remain silent, should draw hints of your next destination from the ``silence", and revise its recommendations as needed. In this paper, we construct a well-timed POI recommender system that updates its recommendations in accordance with the silence, the temporal period in which no visits are made. To achieve this, we propose a novel probabilistic model to predict the joint probabilities of the user visiting POIs and their time-points, by using the admixture or mixed-membership structure to extend marked point processes. With the admixture structure, the proposed model obtains a low dimensional representation for each user, leading to robust recommendation against sparse observations. We also develop an efficient and easy-to-implement estimation algorithm for the proposed model based on collapsed Gibbs and slice sampling. We apply the proposed model to synthetic and real-world check-in data, and show that it performs well in the well-timed recommendation task.

Besides fashion, personalization is another important factor of wearing. How to balance fashion trend and personal preference to better appreciate wearing is a non-trivial task. In previous work we develop a demo, Magic Mirror, to recommend clothing collocation based on the fashion trend. However, the diversity of people’s aesthetics is huge. In order to meet different demand, Magic Mirror is upgraded in this paper, and it can give out recommendations by considering both the fashion trend and personal preference, and work as a private clothing consultant. For more suitable recommendation, the virtual consultant will learn users’ tastes and preferences from their behaviors by using Genetic algorithm. Users can get collocations or matched top/bottom recommendation after choosing occasion and style. They can also get a report about their fashion state and aesthetic standpoint on recent wearing.

Collaborative filtering (CF) is a widely used approach in recommender systems to solve many real-world problems. Traditional CF-based methods employ the user-item matrix which encodes the individual preferences of users for items for learning to make recommendation. In real applications, the rating matrix is usually very sparse, causing CF-based methods to degrade significantly in recommendation performance. In this case, some improved CF methods utilize the increasing amount of side information to address the data sparsity problem as well as the cold start problem. However, the learned latent factors may not be effective due to the sparse nature of the user-item matrix and the side information. To address this problem, we utilize advances of learning effective representations in deep learning, and propose a hybrid model which jointly performs deep users and items’ latent factors learning from side information and collaborative filtering from the rating matrix. Extensive experimental results on three real-world datasets show that our hybrid model outperforms other methods in effectively utilizing side information and achieves performance improvement.

MIT announced today that it's developed a speech recognition chip capable of real world power savings of between 90 and 99 percent over existing technologies. Voice technology has, of course, become nearly ubiquitous in mobile devices, thanks to the exponential growth of smart assistants like Siri, Alexa and Google Home – but the new chip could help branch out in much simpler electronics. The team gives IoT devices a potential use case – devices designed to go months on end without charging or changing batteries. Speech input will become a natural interface for many wearable applications and intelligent devices. The miniaturization of these devices will require a different interface than touch or keyboard.

As Valentine's Day approaches, a recent report shows North Americans lead the rest of the world when it comes to dating app engagement. North America has a dating app subscription rate 7.2 times that of Europe and 2.6 times more than Asia. User acquisition firm Liftoff, released its annual review of dating app trends and insights. Liftoff analyzed nearly three billion dating app ad impressions across more than one million app installs and 3.4 million post-install events in 2016. If you think dating app subscriptions spike just before Valentine's Day, the report shows that's not the case.

Valentine's Day is around the corner, and as people's thoughts turn to love, chocolate, and dating, a new app has been announced with a simple concept: it searches for matches based on photos that users upload of faces they find enticing. Developed by researchers at the New Jersey Institute of Technology (NJIT), the app is called FaceDate. You teach the app what kind of face you like, and it goes from there. Cristian M. Borcea, the chair of the computer science department at NJIT, supervised the graduate students who developed the app. "Someone downloads the app and then has the ability to train the app with faces that that person might like to date," Borcea told Fox News.

In this week's This Feels A Little Like Skynet: IBM built a new voice assistant using artificial intelligence called Hayvn, focused on cybersecurity. Think of it as Amazon Alexa, but instead of ordering soap, it's helping you manage threats. Sure, this might sound like it's ripped straight out of the plot for Terminator 3: Rise of the Machines, in which the military unleashes a new AI called Skynet to fight a virus that's been disrupting worldwide networks. And yes, that AI then becomes sentient, launches nukes and begins "Judgement Day." Here in the real world, IBM said Hayvn is being used to help cybersecurity pros comb through the hundreds of alerts they receive each day.

Hoping to go to Google's annual developer conference this spring? If you are, mark your calendar for Feb. 22. That's the day when you can first apply for tickets to Google I/O. Google announced on its events page that the window for submitting ticket applications is between Feb. 22 at 1 p.m. ET and Feb. 27 at 8 p.m. ET. The conference is being held May 17-19 at the Shoreline Amphitheatre in Mountain View, Calif. This is the second year that the event will be held in Mountain View.

How humanity will meet its end is a an endless source of fascination in science fiction. But scientists claim many of the scenarios depicted in films - such as an asteroid strike and killer robots - may not be as far fetched as you might think. Now researchers at Cambridge University's Study of Existential Risk (CESR) have come up with a list of 10 threats that may some day trigger an apocalypse. Humanity faces an uncertain future as technology learns to think for itself and adapt to its environment. Artificial Intelligence, disguised as helpful digital assistants and self-driving vehicles, is gaining a foothold and it could one day spell the end for mankind if allowed to develop without strict controls.

Every year, innovators and disruptors push the boundaries beyond what we previously thought was possible by introducing new and exciting products to the masses. From all-knowing AI assistants and drones that can transport us, to glasses that record video and a screen that can bend, last year was no different. Tech in 2016 was all about changing the way we experience the world, expanding what our devices can do and developing new ways to make our lives just a little bit easier. We'll revisit the top technology that thrilled us in 2016 and explore why we were so obsessed. Then we'll look ahead to make our best predictions at what 2017 might hold for these seven game changers.