Although a great methodological effort has been invested in proposing competitive solutions to the class-imbalance problem, little effort has been made in pursuing a theoretical understanding of this matter. In order to shed some light on this topic, we perform, through a novel framework, an exhaustive analysis of the adequateness of the most commonly used performance scores to assess this complex scenario. We conclude that using unweighted H\"older means with exponent $p \leq 1$ to average the recalls of all the classes produces adequate scores which are capable of determining whether a classifier is competitive. Then, we review the major solutions presented in the class-imbalance literature. Since any learning task can be defined as an optimisation problem where a loss function, usually connected to a particular score, is minimised, our goal, here, is to find whether the learning tasks found in the literature are also oriented to maximise the previously detected adequate scores. We conclude that they usually maximise the unweighted H\"older mean with $p = 1$ (a-mean). Finally, we provide bounds on the values of the studied performance scores which guarantee a classifier with a higher recall than the random classifier in each and every class.

Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been empirically observed that these same classifiers are relatively robust to random noise. In this paper, we propose to study a \textit{semi-random} noise regime that generalizes both the random and worst-case noise regimes. We propose the first quantitative analysis of the robustness of nonlinear classifiers in this general noise regime. We establish precise theoretical bounds on the robustness of classifiers in this general regime, which depend on the curvature of the classifier's decision boundary. Our bounds confirm and quantify the empirical observations that classifiers satisfying curvature constraints are robust to random noise. Moreover, we quantify the robustness of classifiers in terms of the subspace dimension in the semi-random noise regime, and show that our bounds remarkably interpolate between the worst-case and random noise regimes. We perform experiments and show that the derived bounds provide very accurate estimates when applied to various state-of-the-art deep neural networks and datasets. This result suggests bounds on the curvature of the classifiers' decision boundaries that we support experimentally, and more generally offers important insights onto the geometry of high dimensional classification problems.

We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user-level predictors) which "significantly affect" users. The law will also effectively create a "right to explanation," whereby a user can ask for an explanation of an algorithmic decision that was made about them. We argue that while this law will pose large challenges for industry, it highlights opportunities for computer scientists to take the lead in designing algorithms and evaluation frameworks which avoid discrimination and enable explanation.

We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations. Our new method, called Geometric Resampling (GR), is described and analyzed in the context of online combinatorial optimization under semi-bandit feedback, where a learner sequentially selects its actions from a combinatorial decision set so as to minimize its cumulative loss. In particular, we show that the well-known Follow-the-Perturbed-Leader (FPL) prediction method coupled with Geometric Resampling yields the first computationally efficient reduction from offline to online optimization in this setting. We provide a thorough theoretical analysis for the resulting algorithm, showing that its performance is on par with previous, inefficient solutions. Our main contribution is showing that, despite the relatively large variance induced by the GR procedure, our performance guarantees hold with high probability rather than only in expectation. As a side result, we also improve the best known regret bounds for FPL in online combinatorial optimization with full feedback, closing the perceived performance gap between FPL and exponential weights in this setting.

Google's DeepMind's Health initiative will soon work to explore how artificial intelligence could save hours and hours of precious time in the treatment of oral, head and neck cancers, the company announced on Tuesday. Whatever it is Zuckerberg is calling his personal home AI system. Yesterday he updated an audience in Rome about his personal project this year. He had Facebook (FB) engineers work on a computerized domestic assistant as his personal challenge. The AI controls his AC, lighting, opens his security gate, and can even make him toast.

AI is a field of technology where machines mimic human thinking and reasoning in their processing and carry out tasks usually performed by people. Several people have given various definitions for what actually is AI. Ram Sriharsha, senior architect and machine learning expert at Hortonworks, a data collection and data analytics software company, is quoted in Information Week as describing AI as being "very broad" and says "AI is being able to communicate, being able to plan and reason and take actions". The American author, computer scientist, inventor and futurist Raymond Kurzweil notes the most durable definition of AI is "the art of creating machines that perform functions that require intelligence when performed by people". However, he explains this quote is not a perfect one as it does not always fit "actual usage" and doesn't explain what exactly is meant by "artificial" or "intelligent".

Electric utilities across the U.S. are wasting no time to take advantage of FAA rules authorizing use of drones for commercial purposes. Electric utilities across the U.S. are wasting no time taking advantage of new FAA rules authorizing use of drones for commercial purposes. "We've certainly heard from our members that they're excited about this technology," said Chris Hickling, the director of government relations for the Edison Electric Institute (EEI), the trade group for investor-owned utilities in the U.S. "They see it as part of building a smarter infrastructure. We see it as an area that's going to continue to grow." More than 20 utilities have already tested unmanned aerial vehicles for inspecting transmission and distribution lines for damage from storm and normal wear and tear, using temporary rules from the Federal Aviation Administration, and are now ready to demonstrate them even more.

This file photo taken on March 25, 2015 shows an UBER application shown as cars drive by in Washington, DC. The US ride-sharing service Uber announced August 18, 2016 it had acquired the commercial transport-focused tech startup Otto as the company presses ahead with its pursuit of self-driving technology. The announcement came as the company also announced a 300 million effort with the Sweden-based automaker Volvo Cars to develop driverless cars."If that sounds like a big deal -- well, it is," Uber CEO Travis Kalanick said in a statement. SAN FRANCISCO - Uber has hired Target's chief marketing officer to create a more unified corporate message and strategy for the mushrooming ride-hailing service. Jeff Jones, 48, who joined Target in 2012 with a mission to upgrade the retailer's digital strategy, will become Uber's president of ride-sharing and be responsible for operations, marketing and customer support globally, Uber CEO Travis Kalanick announced in a blog post Tuesday.

It is already changing the face of warface, with AI adversaries and electronic spies taking centre stage. However, America has fallen catastrophically behind in the hi-tech battlefield, a new report has claimed. The Defense Science Board's report into autonomy concluded'there are both substantial operational benefits and potential perils associated with its use,' and called for immediate action. The Defense Science Board's report into autonomy concluded the DoD must accelerate its exploitation of autonomy to remain ahead of enemies. 'This study concluded that DoD must accelerate its exploitation of autonomy--both to realize the potential military value and to remain ahead of adversaries who also will exploit its operational benefits.'

Nasa has announced that it has found evidence of flowing water on Mars. Scientists have long speculated that Recurring Slope Lineae -- or dark patches -- on Mars were made up of briny water but the new findings prove that those patches are caused by liquid water, which it has established by finding hydrated salts. Several hundred camped outside the London store in Covent Garden. The 6s will have new features like a vastly improved camera and a pressure-sensitive "3D Touch" display