Regularization is an essential mechanism in Machine Learning that usually refers to the set of techniques that attempt to improve the estimates by biasing them away from their samplebased values towards values that are deemed to be more "physically plausible" [1]. In practice, it is often used to avoid overfitting, use some prior knowledge about the problem at hand or induce some desirable properties over the resulting learning machine. One of these properties is the so called sparsity, which can be roughly defined as expressing the learning machines using only a part of the training information. This has advantages in terms of the interpretability of the model and its manageability, and also preventing the over-fitting. Two representatives of this type of models are the Support Vector Machines (SVM [2]) and the Lasso model [3], based on inducing sparsity at two different levels. On the one hand, the SVMs are sparse in their representation in terms of the training patterns, which means that the model is characterized only by a subsample of the original training dataset. On the other hand, the Lasso models induce sparsity at the level of the features, in the sense that the model is defined only as a function of a subset of the inputs, hence performing an implicit feature selection.

A qualitative representation $\phi$ is like an ordinary representation of a relation algebra, but instead of requiring $(a; b)^\phi = a^\phi | b^\phi$, as we do for ordinary representations, we only require that $c^\phi\supseteq a^\phi | b^\phi \iff c\geq a ; b$, for each $c$ in the algebra. A constraint network is qualitatively satisfiable if its nodes can be mapped to elements of a qualitative representation, preserving the constraints. If a constraint network is satisfiable then it is clearly qualitatively satisfiable, but the converse can fail. However, for a wide range of relation algebras including the point algebra, the Allen Interval Algebra, RCC8 and many others, a network is satisfiable if and only if it is qualitatively satisfiable. Unlike ordinary composition, the weak composition arising from qualitative representations need not be associative, so we can generalise by considering network satisfaction problems over non-associative algebras. We prove that computationally, qualitative representations have many advantages over ordinary representations: whereas many finite relation algebras have only infinite representations, every finite qualitatively representable algebra has a finite qualitative representation; the representability problem for (the atom structures of) finite non-associative algebras is NP-complete; the network satisfaction problem over a finite qualitatively representable algebra is always in NP; the validity of equations over qualitative representations is co-NP-complete. On the other hand we prove that there is no finite axiomatisation of the class of qualitatively representable algebras.

In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of architectural constraints in subtasks with positive and negative transfer, across a range of network capacities. We empirically show that our augmented DQN has lower sample complexity when simultaneously learning subtasks with negative transfer, without degrading performance when learning subtasks with positive transfer.

Investors hope for billion-dollar health-tech "unicorns". Amid such talk it is worth remembering that the biggest winners from digital health care will be the patients who receive better treatment, and those who avoid becoming patients at all.' – The Economist Machine learning and Artificial Intelligence (AI) continue to transform many aspects of our lives. The potential gains in healthcare are enormous. Although investment in digital healthcare start-ups has doubled since 2013, progress is slow, in part because of regulatory and cost hurdles. Machine learning in healthcare means that organisations can benefit from evolving technological capabilities.

As artificial intelligence proliferates, companies and governments are aggregating enormous data sets to feed their AI initiatives. Although privacy is not a new concept in computing, the growth of aggregated data magnifies privacy challenges and leads to extreme ethical risks such as unintentionally building biased AI systems, among many others. Privacy and artificial intelligence are both complex topics. There are no easy or simple answers because solutions lie at the shifting and conflicted intersection of technology, commercial profit, public policy, and even individual and cultural attitudes. Given this complexity, I invited two brilliant people to share their thoughts in a CXOTALK conversation on privacy and AI.

Today's guest is Sean Lane, CEO of CrossChx, and we have a great chat about artificial intelligence. President Trump met with Juan Manuel the President of Columbia yesterday and held a joint news conference. The President emphasized counter drug trafficking in partnership with Columbia. Other key points include the President's claims that illegal border crossings in the U.S. are down 73%, he wants the U.S. to work with South American countries on the Venezuelan problem, and also promised that MS-13 gang members will be gone from the U.S. soon. President Trump also took to Twitter today as he tweeted, "this is the single greatest witch hunt of a politician in American history!" and "with all of the illegal acts that took place in the Clinton campaign & Obama Administration, there was never a special counsel!" The tweets were in response to Wednesday's news that the Department of Justice appointment former FBI Director Robert Mueller as special counsel to investigate Russian interference in the U.S. presidential election.

AI is constantly touted as the next big thing. But how many of us are aware that AI is already here? While the jury is still out on whether it will be a benevolent force or an existential threat to humankind, AI is active in many facets of our daily lives and will play a larger role in the years to come. For example, the NSA has basically a version of "Skynet" from the Terminator series to track suspected terrorists and predict terrorist attacks (Minority Report, anyone?). And AI "hivemind" UNU correctly predicted the exact final score for this year's Super Bowl.

Your next doctor could very well be a bot. And bots, or automated programs, are likely to play a key role in finding cures for some of the most difficult-to-treat diseases and conditions. Artificial intelligence is rapidly moving into health care, led by some of the biggest technology companies and emerging startups using it to diagnose and respond to a raft of conditions. While technology has always played a role in medical care, a wave of investment from Silicon Valley and a flood of data from connected devices appear to be spurring innovation. "I think a tipping point was when Apple released its Research Kit," said Forrester Research analyst Kate McCarthy, referring to a program letting Apple users enable data from their daily activities to be used in medical studies.

Even though Finland-based unloaded its mobile handset business on in 2014, it remains the second-largest mobile equipment manufacturer in the world after Sweden-based . The company has about 100,000 employees after its acquisition of in 2016. Microsoft shuttered the handset business a scant two years after the company acquired it, freeing up hundreds of skilled technical resources, especially in Oulu, as I discussed in my last article. In spite of these disruptions, Nokia still employs over 2,000 people in this small city near the Arctic Circle. In fact, the company still operates a factory there, manufacturing mobile base stations for telco service providers.

The rise of Artificial Intelligence (AI) technology could be set to shake up the job scene in the UK sooner than expected, new research shows. A BT survey of over 1,500 senior UK IT decision makers found that AI, widely expected to usher in the "fourth industrial revolution," is in fact already splitting opinions in the labor market. On the positive side, a third of businesses which say they plan to introduce AI or automation technologies within the next two years believe it will create more jobs within the workplace. However, a similar amount of respondents also feared that implementing such services would lead to job losses, as robotic or automated procedures replaced trained human workers. Overall, one in four of the organizations surveyed say they are already using automation technologies, with the likes of drones, robots or autonomous vehicles proving popular.