This paper tackles the problem of endogenous link prediction for knowledge base completion. Knowledge bases can be represented as directed graphs whose nodes correspond to entities and edges to relationships. Previous attempts either consist of powerful systems with high capacity to model complex connectivity patterns, which unfortunately usually end up overfitting on rare relationships, or in approaches that trade capacity for simplicity in order to fairly model all relationships, frequent or not. In this paper, we propose Tatec, a happy medium obtained by complementing a high-capacity model with a simpler one, both pre-trained separately and then combined. We present several variants of this model with different kinds of regularization and combination strategies and show that this approach outperforms existing methods on different types of relationships by achieving state-of-the-art results on four benchmarks of the literature.

We represent knowledge as integrity constraints in a formalization of probabilistic spatio-temporal knowledge bases. We start by defining the syntax and semantics of a formalization called PST knowledge bases. This definition generalizes an earlier version, called SPOT, which is a declarative framework for the representation and processing of probabilistic spatio-temporal data where probability is represented as an interval because the exact value is unknown. We augment the previous definition by adding a type of non-atomic formula that expresses integrity constraints. The result is a highly expressive formalism for knowledge representation dealing with probabilistic spatio-temporal data. We obtain complexity results both for checking the consistency of PST knowledge bases and for answering queries in PST knowledge bases, and also specify tractable cases. All the domains in the PST framework are finite, but we extend our results also to arbitrarily large finite domains.

No longer the exclusive domain of data-reliant businesses like Google, Microsoft, and Amazon, Machine learning has been making its way to the masses as an essential approach to data. Today, machine learning is understood and accepted by a more mainstream audience, and has become a measurable driver for big business both on and offline. There are three key reasons why machine learning has become one ofthe top 10 strategic technology trendsthat will shape digital business opportunities through 2020. First, the volume of data companies now collect is so massive that many struggle to make sense of it. Machine learning allows companies to take advantage of the information they already have.

Here are choice articles on hot leadership topics culled from the business schools, the business press and major consulting firms, to start off your work week. Highlights include leading in the digital age, changing the game in industrial goods through digital services, the rise of machine learning, how women and men internalise the glass ceiling, and the explosion of wearing work on our wrists. Note: Some links require you to register or are to publications that have some form of limited paywall. "Servant leadership is not a new concept. Robert Greenleaf introduced the idea back in 1977. In recent years, however, concrete evidence has emerged that the approach delivers more than warm, fuzzy feelings. Last month, the first quantitative study that begins to explain a connection between servant leadership and improved individual performance was published by researchers in Canada. This new evidence may help move servant leadership from a niche practice to one adopted by more executives."

One of the most hotly contested bits of real estate today is one you can't see. As we move into an increasingly wireless-connected world, staking out a piece of the crowded electromagnetic spectrum becomes more important. DARPA is hoping to help solve this issue with its latest Grand Challenge, which calls for the use of machine-learning technologies to enable devices to share bandwidth. The Spectrum Collaboration Challenge (SC2) is aimed at alleviating an ongoing technological headache. Ever since the invention of radio, it's been recognized that there is only so much of the electromagnetic spectrum to go around, so government regulations were imposed to allocate bandwidth.

Artificial Intelligence is just around the corner. Of course, it's been just around the corner for decades, but in part that's our own tendency to move the goalposts about what'intelligence' is. Once, playing chess was one of the smartest things you could do. Now that a computer can easily beat a Grand Master, we've reclassified it as just standard computation, not requiring proper thinking skills. With the rise of deep learning and the proliferation of machine learning analytics, we edge ever closer to the moment where a computer system will be able to accomplish anything and everything better than a human can. So should we start worrying about SkyNet?

Last week we previewed this in "How Machine Learning APIs are Being Used to Predict Startup Success." Can there be a quantifiable way to hedge investors' risk and ensure they are betting on the right horse? According to the startup "jury" algorithm PreSeries, it's mathematically probable to predict which startup is most likely to succeed and that startup is Novelti. This startup which uses online machine-learning algorithms to convert Internet of Things sensor data into real-time intelligence, machine learning and pattern recognition was predicted to be successful with an 87 percent likelihood. Novelti beat out four other predictive analytics and artificial intelligence competitors--Intranetum, Emotion Research Lab, Datatrics and restb--at the PAPIs Connect conference for machine learning and predictive APIs.

Figuring out where to live is never easy. Do you settle in the house next to the elementary school or the one a few miles away that's cheaper? You decide to confide in your robotic assistant, who asks you a series of questions about what's most important to you: Nearby schools, bars, or parks? After some back-and-forth, it tells you your affordable dream home is two miles away from a reputable public school. Within the next decade, bots (in our phones and not) will be able to do that and more, says Andrew Moore, the dean of Carnegie Mellon's School of Computer Science.

This class is self paced. You can begin whenever you like and then follow your own pace. It's a good idea to set goals for yourself to make sure you stick with the course. Take a look at the "Class Summary," "What Should I Know," and "What Will I Learn" sections above. If you want to know more, just enroll in the course and start exploring.

Telstra Network Disruptions challenged Kagglers to predict the severity of service disruptions on their network. Using a dataset of features from their service logs, participants were tasked with predicting if a disruption was a momentary glitch or a total interruption of connectivity. Mario Filho, a self-taught data scientist, took first place in his first "solo win". In this blog, he shares a high-level view of his approach. My background in machine learning is completely "self-taught". It all began in 2012 when I decided to learn Calculus on my own through the videos from a MIT class.