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.

Sure, most of us only have to deal with it once in a while, but for CNN foreign correspondent Will Ripley it's a frequent foe. "Blackout curtains and melatonin" are a must according to Ripley. "I take a lot of vitamins. You're staying in different hotels, you're eating different foods; you want to make sure that you stay healthy and have stamina for working around the clock." Since becoming the American cable news network's Tokyo bureau chief in March 2014, the 35-year-old Connecticut native has been sent to the Middle East twice, China around a dozen times and North Korea seven times.

Where it applies, it heatedly enables data-rich and knowledge-lean automation of valuable tasks of perception, classification and numeric prediction. Let's consider where learning or discovery best applies -- and why this matters for business. Years ago I was a machine-discovery researcher. Scholarly articles were published in the journal Machine Learning, and presentations were made at Machine Learning conferences, since it seemed that learning and discovery were similar human activities. As a (veteran) entrepreneur, I'm often asked whether a learning approach makes sense for automating some task, which motivated me to pen this piece.

TECH ENTREPRENEUR Elon Musk has been warning that the Age of the Robots is coming soon -- and it might not be pleasant for us. He may be right and he may be wrong on that, but one thing is sure: One robot certainly gave the anti-Whites a headache just this week. On Wednesday, tech giant Microsoft, the third largest corporation on Earth in terms of market value, launched and then immediately withdrew an Artificial Intelligence robot in the persona of a 19-year-old American girl called "Tay." Tay was a "chatbot," which interacted with real humans on the social media platform Twitter and was designed to learn from its interactions. Tay learned so fast that Microsoft pulled her offline in less than a single day.

By now, the fact that transatlantic democratic capitalism, once the engine of postwar prosperity, has run into trouble can hardly be denied by anyone with the courage to browse a daily newspaper. Hunger, homelessness, toxic chemicals in the water supply, the lack of affordable housing: all these issues are back on the agenda, even in the most prosperous of countries. This appalling decline in living standards was some time in the making – 40 years of neoliberal policies are finally taking their toll – so it shouldn't come as a shock. However, coupled with the spillover effects of wars in the Middle East – first the refugees, now the increasingly regular terrorist attacks in the heart of Europe – our economic and political malaise looks much more ominous. It's hardly surprising that the insurgent populist forces, on both left and right, have such an easy time bashing the elites.

The United States announced earlier this month that it had used both drones and manned aircraft to kill at least 150 al-Shabab fighters in Somalia, a move the Pentagon says was necessary to stop an imminent attack on US and African Union forces in the country. Critics of the US drone programme however, argue such strikes create more enemies than they kill. With the number of fighters joining al-Shabab having nearly doubled since 2013, how can the armed group be defeated? In this week's Arena, Somalia's former special envoy to the US Abukar Arman, who has called drone strikes a "priceless propaganda tool" for al-Shabab, is in debate with the country's former deputy prime minister Ahmed Abdisalam Adan, who says the strikes are needed. Follow UpFront on Twitter @AJUpFront and Facebook.

The Lost World: Jurassic Park 1997 AMC Sun. Tomorrow Never Dies 1997 EPIX Wed. 10 p.m., Thur. The X-Files: Fight the Future 1998 IFC Thur. Hard to Kill 1990 Sundance Mon. 8 p.m., Tue. A scientist gives his bodyguard superhuman powers in order to fight racists. A lawyer unwittingly becomes friends with an unstable woman who has a criminal history. A successful businesswoman puts her family, career and life on the line to satisfy her addiction to sex. With his father trapped in the wreckage of their spacecraft, a youth treks across Earth's now-hostile terrain to recover their rescue beacon and signal for help. In the future a cutting-edge android in the form of a boy embarks on a journey to discover his true nature. An 11-year-old boy experiences the worst day of his young life but soon learns that he's not alone when other members of his family encounter their own calamities. A struggling writer falls in love with a stenographer while trying to finish his new novel in 30 days.

This week, a short novel written by an AI program did well in a Japanese literary contest, scientists spotted traces of a possible new particle that could shake the foundations of physics and a team of researchers discovered in the human genome a "nearly intact" genetic blueprint for a 700,000-year-old stowaway virus. A short novel written by a Japanese artificial intelligence software program passed the first screening round for the Nikkei Hoshi Shinichi Literary Award. "The day a computer wrote a novel," the program wrote near the end of the piece, "the computer, placing priority on the pursuit of its own joy, stopped working for humans." A team of scientists from Tufts University and the University of Michigan Health System has found a "nearly intact" genetic copy of an ancient virus that spliced itself into our DNA. The team doesn't rule out the possibility that it could come alive again.

In an unassuming, two-story Victorian town house in Bristol, people are being filmed, monitored, and tracked 24/7. Invisible sensors constantly keep a watchful eye as they go about their business. But what these folks lose in privacy could be our collective gain in life expectancy--that is, if the long-term data bears out. Pivotal to the 15-million ( 21M) Sensor Platform for Healthcare in a Residential Environment (SPHERE) project, this house has been invisibly fitted with dozens of cameras and sensors while its occupants are asked to don wearable devices. The aim is to research how health is related to everyday lifestyle and living conditions over time.

LONDON/BRUSSELS – Facial recognition software, scanners that detect weapons and cameras that spot nervous people are some of the technologies that could be used more widely to secure public places, but some would require greater acceptance of surveillance in Europe. The deadly attacks in Brussels on Tuesday highlighted the vulnerability of Europe's airports and transport systems. European Union officials, grappling with the conundrum of how to increase security while retaining the openness of society, have convened meetings to discuss aviation and land transport security. Their goal is to be able to monitor passengers unobtrusively while minimizing additional hold ups that create crowds, which can themselves become new targets. Experts say technology cannot solve the problem on its own, but techniques such as facial recognition able to pick out known suspects can help if Europeans decide they want more surveillance.